Pith. sign in

Paper Citation Record · LEDGER

Distribution-Aware Feature Selection for SAEs

As of 22 August 2026, this Paper Citation Record lists 13 of 13 outbound references and 0 inbound Pith citation observations for arXiv:2508.21324.

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

pith.paper-citation-record.v1
2508.21324 v1

Coverage vector

measured 13 of 13 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T14:27:25.454156Z

measured 13 of 13 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

13 of 13 outbound references displayed

  • verified exact0
  • verified fuzzy4
  • unresolved9
  • parse uncertain0
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

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

This paper cites SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability.

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.

source=pdf_text observed=2026-08-05T14:27:25.439860Z digest=sha256:83bda659fb49670a41f3f2b7cf9f82e4ad8ab49feec8bd496f01870036369782

Observation 96cfe9ce-a37d-41f3-9def-752e842cb6ed · outbound

This paper cites Sparse Autoencoders Trained on the Same Data Learn Different Features.

Distribution-Aware Feature Selection for SAEs Sparse Autoencoders Trained on the Same Data Learn Different Features

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.446156Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.446156Z digest=sha256:f45d8951a86d69e40830cdf3b64e880ce640e7bcd15845d3dad06e2ef17fb56e

Observation c04e6590-8c83-4c82-909d-740fa0f5ac6a · outbound

This paper cites activation lottery.

Distribution-Aware Feature Selection for SAEs activation lottery

Reference 12

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:27:25.599812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-05T14:27:25.454156Z digest=sha256:d14771a6cca677eaebf61ddaea5a0c31c3fd29400673adf4b5b5dc9b32e2333d

Observation f4ba490c-26f2-40af-afd2-8114fd7b3b5f · outbound

This paper cites High frequency latents are features, not bugs.

Distribution-Aware Feature Selection for SAEs High frequency latents are features, not bugs

Reference 13

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:27:25.609772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-05T14:27:25.451622Z digest=sha256:e7b289a5c5bb90cc330be06161b529cb50d02117dd18b6a798a5076ba0a8b076

Observation de1f2a05-692c-493d-acd3-caa96f5d87da · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Distribution-Aware Feature Selection for SAEs The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 2004

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.430598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.430598Z digest=sha256:d06ea230d6433681fa3a877828632b64ec29efb9af433c806ebc359fcaf6943c

Observation faf94b8e-5da5-4fb6-b848-1c0faa36b836 · outbound

This paper cites Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition.

Distribution-Aware Feature Selection for SAEs Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition

Reference 2009

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.414379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.414379Z digest=sha256:01cab9a2f0413d039016702860bbb6e3109b3390e2cc75565bb6413406c57235

Observation d186e98d-a9c8-4a13-a445-c6d7c0511051 · outbound

This paper cites Online row sampling.

Distribution-Aware Feature Selection for SAEs Online row sampling

Reference 2015

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:27:25.617473Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-05T14:27:25.424101Z digest=sha256:814cdd442552469bf2c4d42ebc942ca63f9e41bfcc580b73b7bbd03c58184dc0

Observation c5b71cd4-73d5-4923-b094-3d5c2d3cb41a · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Distribution-Aware Feature Selection for SAEs Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 2016

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.436740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.436740Z digest=sha256:31081d3bb912c8f202842adf782143004db8f3566ef39bec99bb2496fed16feb

Observation ff08ff48-df8c-4a13-b271-604b726fe0b5 · outbound

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

Distribution-Aware Feature Selection for SAEs Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 2017

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.427171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.427171Z digest=sha256:c2fa9b02246566ca25ae1cb2e56a823dddd8e9df84507330c46509d58b6fc1ee

Observation 83ed672f-fb79-42bb-a6ad-a2f7a6671e5b · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Distribution-Aware Feature Selection for SAEs Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 2020

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.433612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.433612Z digest=sha256:ab83df1385181e7732f438cf8a202515ca8223e7dd4636da8f7c2652d064f3b0

Observation 9715d8c0-cb74-4c08-8466-e1f0af7674b3 · outbound

This paper cites Bart Bussmann, Joseph Jermyn, and Nix Robertson.

Distribution-Aware Feature Selection for SAEs Bart Bussmann, Joseph Jermyn, and Nix Robertson

Reference 2023

Resolution
verified fuzzy
raw_fallback, observed 2026-08-05T14:27:25.625688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

source=pdf_text observed=2026-08-05T14:27:25.418043Z digest=sha256:1fb83493906f34c15d3f538d6aa7f5d74c7ff6ac1bfe419e64746220a95586de

Observation 8712a6ef-8836-44d3-9563-67d00474fb30 · outbound

This paper cites David Chanin, James Wilken-Smith, Tomáš Dulka, Hardik Bhatnagar, Satvik Golechha, and Joseph Bloom.

Distribution-Aware Feature Selection for SAEs David Chanin, James Wilken-Smith, Tomáš Dulka, Hardik Bhatnagar, Satvik Golechha, and Joseph Bloom

Reference 2024

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.420785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.420785Z digest=sha256:2d575ebe23b4622c5692e8aac3024322fd4ec7e70720b4855b8e9ee53f1975b4

Observation 38cada16-d398-4e83-9f60-d806293f9950 · outbound

This paper cites Automatically Interpreting Millions of Features in Large Language Models.

Distribution-Aware Feature Selection for SAEs Automatically Interpreting Millions of Features in Large Language Models

Reference 2025

Resolution
unresolved
no resolver link, observed 2026-08-05T14:27:25.448907Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-05T14:27:25.448907Z digest=sha256:5e702bea5d6e2b7d5e28c3b68c480aa06a9602c7578232316ab33d7576364a82

Pith citing papers

No inbound Pith citation observations are available.