© 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 · 23-RESID-POST-AA · 96531 ｜ Neuronpedia

Home
Andy Arditi · GPT-OSS BatchTopK SAEs
GPT-OSS-20B
Resid Post - 131k
23-RESID-POST-AA
96531

INDEX

Explanations

paragraphs

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_23/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

sef

-0.09

 files

-0.09

 simulations

-0.08

 haren

-0.08

 cabins

-0.08

 zeros

-0.08

 života

-0.08

 Zugang

-0.07

 ستون

-0.07

 والي

-0.07

POSITIVE LOGITS

 paragraph

0.21

 paragraphs

0.21

Paragraph

0.20

paragraph

0.20

 Paragraph

0.18

 sentences

0.15

 parag

0.14

sentence

0.14

 pár

0.13

-par

0.13

Activations Density 0.036%

No Known Activations