Paper Citation Record · LEDGER

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

As of 17 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 5 inbound Pith citation observations for arXiv:2411.13117.

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

pith.paper-citation-record.v1
2411.13117 v2

Coverage vector

measured 20 of 20 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T16:57:56.622402Z

measured 25 of 25 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-17T06:30:58.91139+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:03:02.401440Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-30T21:15:04.062112Z

Reference resolution

20 of 20 outbound references displayed

verified exact0
verified fuzzy7
unresolved13
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b522c0d5-7cbe-4868-83b3-297d80ff5a21 · outbound

This paper cites Sparse Autoencoders Find Highly Interpretable Features in Language Models.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.541315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c02345-d25f-436c-86ed-2602ca605bd5 · outbound

This paper cites Interpreting Attention Layer Outputs with Sparse Autoencoders.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Interpreting Attention Layer Outputs with Sparse Autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.564805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1b087bb-efcb-4236-88d4-f22bba2903e7 · outbound

This paper cites Identifying Interpretable Visual Features in Artificial and Biological Neural Systems.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Identifying Interpretable Visual Features in Artificial and Biological Neural Systems

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.569271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b556f371-1a9b-4c5b-9447-cd54f4b9687b · outbound

This paper cites Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.573507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bae620f-83dc-455a-a505-8a18a427fb06 · outbound

This paper cites Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.577846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b436d420-31d6-48eb-8072-404e58ad0063 · outbound

This paper cites org/posts/C5KAZQib3bzzpeyrg/ full-post-progress-update-1-from-the-gdm-mech-interp-team.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders org/posts/C5KAZQib3bzzpeyrg/ full-post-progress-update-1-from-the-gdm-mech-interp-team

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:57:56.964754Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f5c291b7-0e21-434c-8149-4618d67896bb · outbound

This paper cites A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders A Survey on Understanding, Visualizations, and Explanation of Deep Neural Networks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.601133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 369990ef-9e46-4dda-8c25-7f040d21ea46 · outbound

This paper cites 2 2.2 Superposition in Neural Representations.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders 2 2.2 Superposition in Neural Representations

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:57:56.930737Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6db00748-dbc4-44d6-ba1b-2eae95341338 · outbound

This paper cites an unresolved cited work.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-12T16:57:56.912674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ad686ba7-1977-408c-9163-e38ad86d592b · outbound

This paper cites This assumption enables high-probability success on most sampled codes, but does not guarantee recovery of all codes.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders This assumption enables high-probability success on most sampled codes, but does not guarantee recovery of all codes

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:57:56.892804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation db94d7c6-d6d0-4b26-994d-0bb6e51dbb78 · outbound

This paper cites negative interference.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders negative interference

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:57:56.847102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0e6bd978-157c-4682-870b-49d68049c352 · outbound

This paper cites total FLOPs Figure 8: (Larger N, M and K) Performance comparison of SAE and MLPs in predicting known latent representa- tions.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders total FLOPs Figure 8: (Larger N, M and K) Performance comparison of SAE and MLPs in predicting known latent representa- tions

Reference 256

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:57:56.866822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 26c258dc-142d-4b52-8e2f-6ee3b4ebc43c · outbound

This paper cites The Geometry of Categorical and Hierarchical Concepts in Large Language Models.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Reference 1997

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.586995Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3059234e-e5b6-4b00-bc08-7f274e50f654 · outbound

This paper cites Toy Models of Superposition.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Toy Models of Superposition

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.545973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45d0b549-586b-4572-8c07-0a0abeae12e5 · outbound

This paper cites Language models can explain neurons in language models.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Language models can explain neurons in language models

Reference 2008

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.535952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b477b97-4302-444e-81eb-3ba6b7549e63 · outbound

This paper cites To- ward transparent ai: A survey on interpreting the inner structures of deep neural networks.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders To- ward transparent ai: A survey on interpreting the inner structures of deep neural networks

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:57:56.950928Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation cebf63c4-fe58-4603-a378-fb4e45a02552 · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.591629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cac415a0-38be-4670-8a10-0e376379bd2e · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders Scaling and evaluating sparse autoencoders

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.551037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85784940-e361-44f2-991b-66080b3876b4 · outbound

This paper cites org/posts/KzwB4ovzrZ8DYWgpw/ more-findings-on-memorization-and-double-descent.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders org/posts/KzwB4ovzrZ8DYWgpw/ more-findings-on-memorization-and-double-descent

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T16:57:56.977359Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fd869792-820f-40ba-b38b-e312bfda19ac · outbound

This paper cites The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision.

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-12T16:57:56.555299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 80efe505-6c96-40c4-806b-a586fdc29537 · inbound

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs cites this paper.

Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:03:02.401440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60780d5f-74a1-4385-9266-7171d2fca26a · inbound

Towards Atoms of Large Language Models cites this paper.

Towards Atoms of Large Language Models Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T15:20:32.189070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8e9d419-4a36-4703-b04e-0132ba5e24e8 · inbound

The Rate-Distortion-Polysemanticity Tradeoff in SAEs cites this paper.

The Rate-Distortion-Polysemanticity Tradeoff in SAEs Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:15:04.064124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c80f9484-f02d-4bb3-9f08-95fb4162280a · 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 Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Reference 20

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T14:23:30.755282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 9c450dd6-7568-4c30-a481-f097195c9688 · 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 Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T05:02:51.324984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.