© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

GPT-OSS-20B · 19-RESID-POST-AA · 102573 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
19-RESID-POST-AA
102573

INDEX

Explanations

Table of contents

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0

Dataset (Dashboard)

Various

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 clipped

-0.10

clip

-0.10

 Clip

-0.09

 clip

-0.09

Clip

-0.09

 plated

-0.09

_clip

-0.09

 clipping

-0.09

 elliptical

-0.09

裁

-0.08

POSITIVE LOGITS

TO

0.12

toc

0.09

 Tower

0.09

toc

0.08

 tower

0.08

TO

0.08

.depth

0.08

 recursive

0.08

 टू

0.08

.internal

0.08

Activations Density 0.001%

No Known Activations