Paper Citation Record · LEDGER

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization

As of 6 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2606.08496.

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

pith.paper-citation-record.v1
2606.08496 v1

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-06-27T18:35:47.513717Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+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

41 of 41 outbound references displayed

verified exact4
verified fuzzy0
unresolved31
parse uncertain0
malformed identifier0
metadata mismatch6

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1ad444f6-5a5c-4b00-aae5-d9b74ace4ec7 · outbound

This paper cites Aho and Jeffrey D.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Aho and Jeffrey D

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da5cf5ed-caba-4012-b729-99f19c0c57fe · outbound

This paper cites an unresolved cited work.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08b5d8b5-3acf-4754-80a0-3dbcac33076d · outbound

This paper cites Chandra and Dexter C.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Chandra and Dexter C

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-27T18:41:07.943145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e3c297d8-9661-4e5c-b3bc-097ce78039bf · outbound

This paper cites Scalable training of.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Scalable training of

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a81e7c9f-e256-4b26-9d5a-06b488361d9c · outbound

This paper cites an unresolved cited work.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Unresolved cited work

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a668146-a8cf-403b-897e-2afed1f90f34 · outbound

This paper cites Tetreault , title =.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Tetreault , title =

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc3909fe-5edd-448f-b543-0ac0125eda26 · outbound

This paper cites A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data , Volume =

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbb3337a-abd2-4f2c-b1d2-808a4728ed50 · outbound

This paper cites A Survey of Large Language Models.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization A Survey of Large Language Models

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:57:25.982792Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2b32f1a9-40d4-4501-b24a-c1ed8a1c651e · outbound

This paper cites 2021 , journal=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2021 , journal=

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcda9964-31db-486a-9137-3f492f6b3e9f · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bbbd0d9-2d59-4f17-b1b0-943dea600f32 · outbound

This paper cites Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing , pages=

Reference 11

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 57ba8fd8-4357-46af-afe5-620984375ab0 · outbound

This paper cites International Conference on Learning Representations , volume=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization International Conference on Learning Representations , volume=

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b64bf1c-8d8f-433c-be18-492314bc56b4 · outbound

This paper cites 2023 , journal=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2023 , journal=

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a92013e-bd16-4b2e-81e3-4d5db2807fa3 · outbound

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

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:57:25.993498Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b181e797-929f-4ab2-8728-9054461e9bc4 · outbound

This paper cites 2022 , journal=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2022 , journal=

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05289afe-4dea-493d-86d1-88a09c942a0a · outbound

This paper cites 2023 , howpublished =.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2023 , howpublished =

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27984a4c-a49a-4dee-ba8d-5472582c9d70 · outbound

This paper cites an unresolved cited work.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d66c6fd-c76c-448e-8033-24166c2740fa · outbound

This paper cites ICLR, 2025.https://arxiv.org/abs/2412.08686.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization ICLR, 2025.https://arxiv.org/abs/2412.08686

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.991123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 559a3ae9-838d-46cf-b62b-a04f3f25ec01 · outbound

This paper cites ArXiv , year=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization ArXiv , year=

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 030c3517-e0b6-400c-bee3-7d2b304ab10e · outbound

This paper cites GPT-4 Technical Report.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization GPT-4 Technical Report

Reference 20

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:57:25.997818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7022aec4-39de-4727-80bd-e0b8efa50db8 · outbound

This paper cites an unresolved cited work.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c03c9432-b8ee-4d8c-85aa-28f1d4ac3331 · outbound

This paper cites International Conference on Learning Representations , volume=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization International Conference on Learning Representations , volume=

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bf6a163-827e-488c-9ff5-71eb315a42ac · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Gemma 2: Improving Open Language Models at a Practical Size

Reference 23

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:57:25.995144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a37178b1-2a39-40d3-affc-eb67c10656cf · outbound

This paper cites ArXiv , year=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization ArXiv , year=

Reference 24

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b53d70c8-d53c-478c-a669-63207263afc5 · outbound

This paper cites 2024 , url=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2024 , url=

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9673bbd4-9b5d-4d2a-9a34-5b6e5a9dcf23 · outbound

This paper cites Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP , pages=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Proceedings of the 7th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP , pages=

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4e45c12-8ed9-4917-9d5c-43614a69f623 · outbound

This paper cites ArXiv , year=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization ArXiv , year=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dde8f8d9-d6ff-4877-a79b-a5bccc316f35 · outbound

This paper cites 2024 , url=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2024 , url=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 491bfac9-8d56-4005-bb77-289d76ef0b94 · outbound

This paper cites 2026 , eprint=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2026 , eprint=

Reference 29

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cffb29d-776d-4955-9b39-c542a8a2e11b · outbound

This paper cites Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) , pages=

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30890d41-edf9-429e-83c1-b0ffccb7a5da · outbound

This paper cites Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track) , pages=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 5: Industry Track) , pages=

Reference 31

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a619e1f6-f4c4-4635-b391-39525541d75d · outbound

This paper cites Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP , pages=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Proceedings of the 6th BlackboxNLP Workshop: Analyzing and Interpreting Neural Networks for NLP , pages=

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a352624-5637-41aa-a792-e8a676ff87a4 · outbound

This paper cites 2024 , month =.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2024 , month =

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef606b05-1a76-48ba-814f-3fdbe922430b · outbound

This paper cites Findings of the Association for Computational Linguistics: ACL 2024 , pages=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Findings of the Association for Computational Linguistics: ACL 2024 , pages=

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3caf54b0-a883-4c84-85a5-80e605dc1aeb · outbound

This paper cites Improving Steering Vectors by Targeting Sparse Autoencoder Features.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Improving Steering Vectors by Targeting Sparse Autoencoder Features

Reference 35

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.979965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2818898b-3b77-4064-9fbe-7524327f9630 · outbound

This paper cites Towards Unifying Interpretability and Control: Evaluation via Intervention.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Towards Unifying Interpretability and Control: Evaluation via Intervention

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:25.996505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b22810d4-02f7-4524-8a53-5d68d9cb0cda · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 37

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T22:57:25.998880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 52180db1-e619-46f7-9ca5-f1db35e8ddec · outbound

This paper cites Distill , volume=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Distill , volume=

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ffd95b3-ce31-4606-902a-cf1f63dc9dc1 · outbound

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

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Automatically Interpreting Millions of Features in Large Language Models

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T22:57:25.986871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c2758295-a72a-4ab0-a289-3e581ffced64 · outbound

This paper cites Forty-first International Conference on Machine Learning , year=.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization Forty-first International Conference on Machine Learning , year=

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a52591a-39e1-4332-a1b7-b42388990864 · outbound

This paper cites 2025 , month =.

SAEExplainer: Interpreting SAE Features with Activation-Guided Preference Optimization 2025 , month =

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-27T18:35:47.513717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.