Paper Citation Record · LEDGER

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 24 inbound Pith citation observations for arXiv:2503.09532.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2503.09532 v4

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 24 of 24 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 24 of 24 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T13:29:00.171371Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T10:29:45.394907Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 82a4d355-2fc2-4888-a10d-f5e945759d3e · inbound

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy cites this paper.

Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracy SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:25.837701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19903c6d-936d-43b0-9afe-7f2362cf3100 · inbound

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures cites this paper.

Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T11:56:15.179663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 620053fa-a4fe-44e0-a804-5c35444fc6ec · inbound

Resa: Transparent Reasoning Models via SAEs cites this paper.

Resa: Transparent Reasoning Models via SAEs SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T04:45:42.719642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a50bec3-c959-4b47-af7f-34a36a929314 · inbound

Evaluating SAE interpretability without explanations cites this paper.

Evaluating SAE interpretability without explanations SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T18:24:51.180244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4112d7ac-bf41-414e-88b3-355f5663fc65 · inbound

On the transferability of Sparse Autoencoders for interpreting compressed models cites this paper.

On the transferability of Sparse Autoencoders for interpreting compressed models SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:45.744009Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c41650a-07f1-43c6-bec8-c9c5004543f8 · inbound

Distribution-Aware Feature Selection for SAEs cites this paper.

Distribution-Aware Feature Selection for SAEs SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T14:27:25.439860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00bc17a8-ec58-433b-9b25-7291e4291f8c · inbound

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework cites this paper.

Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-18T18:16:43.748207Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation eb0d2f34-a1c1-4baa-98c7-71091dd817b0 · inbound

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models cites this paper.

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 148

Resolution: verified exact; arxiv_id, observed 2026-05-16T12:40:54.605878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1e7376d5-7454-4840-8813-48c7a2539620 · inbound

Stable and Steerable Sparse Autoencoders with Weight Regularization cites this paper.

Stable and Steerable Sparse Autoencoders with Weight Regularization SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T18:56:20.000242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f372237d-5f3a-434a-9a9c-253ec13b55e8 · inbound

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs cites this paper.

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:35:57.627704Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 41ce46e6-8ce3-437d-9d3d-838688b499cf · inbound

Structural Instability of Feature Composition cites this paper.

Structural Instability of Feature Composition SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T06:41:36.519790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fc8f724e-4403-4fbb-96fc-6f84e4825e25 · inbound

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features cites this paper.

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:16:11.060148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 12da451f-70cb-4dca-a9f9-1ce293485063 · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:15:54.303210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 793d19d5-c2a0-4e38-a5d5-813223894e8a · inbound

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders cites this paper.

Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:16:25.445401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 47bdda45-8ee3-4658-8620-e9586d64adf1 · inbound

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds cites this paper.

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-12T03:16:19.139898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6ec363f6-219e-438e-a626-a06e5bd5fef3 · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:23:30.730641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a84392a0-db3d-4784-95e6-381b677202d3 · inbound

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations cites this paper.

Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.380352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4091bcb3-81ce-41b3-8e70-c13ca7a8f2df · inbound

A Unifying Framework for Concept-Based Representational Similarity cites this paper.

A Unifying Framework for Concept-Based Representational Similarity SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-03T00:27:29.987745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2e6d96a4-bc02-44ab-b873-98d8a489405f · inbound

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? cites this paper.

Do Sparse Autoencoders Learn Meaningful Concept Hierarchies? SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:29:45.396552Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 054b1070-4bea-4917-a1ad-4f0284afe438 · inbound

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models cites this paper.

Persistent Sparse Autoencoders: Learning Feature Timescales in Language Models SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T19:02:29.759226Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7c1800e-f602-48f6-ab03-8968566103d0 · inbound

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression? cites this paper.

Decoder-Preserving Sparse Autoencoders: Which Readouts Survive Sparse Compression? SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T18:04:18.007688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b87c7a6c-e658-41fd-ac48-2b0833781747 · inbound

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects cites this paper.

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T10:03:56.301338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 959c6a7f-12e1-46eb-8ee7-0a5a4c151dd9 · inbound

ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders cites this paper.

ECG-InterpBench: Benchmarking the Interpretability of ECG Foundation Models with Matched-Scale Sparse Autoencoders SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T07:58:32.246258Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbbd8f16-e1d9-4f43-a074-7d7f632f70ea · inbound

Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation cites this paper.

Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-14T13:29:00.171371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.