© 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 · 7-RESID-POST-AA · 937 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
7-RESID-POST-AA
937

INDEX

Explanations

Deep learning and "Real World"

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-gpt-oss-20b/resid_post_layer_7/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

 intellect

-0.09

_imgs

-0.08

�്ച

-0.08

 Tommy

-0.08

 Gentleman

-0.08

كرة

-0.08

-role

-0.08

 We're

-0.08

 intelectual

-0.08

 Cognitive

-0.07

POSITIVE LOGITS

0.07

 either

0.07

 entweder

0.07

 sichern

0.07

ple

0.07

nur

0.07

 enten

0.07

KS

0.07

plete

0.07

NW

0.07

Activations Density 0.000%

No Known Activations