© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 24826
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evenings
    -0.09
     laik
    -0.09
    农村
    -0.08
     vuestro
    -0.08
     refinement
    -0.08
     yrs
    -0.08
     essays
    -0.08
     প্ৰথম
    -0.08
     reign
    -0.07
     vetted
    -0.07
    POSITIVE LOGITS
    Anime
    0.10
     Pokémon
    0.10
     corrupted
    0.09
     pokemon
    0.09
     enemies
    0.09
     zomb
    0.09
     destroying
    0.09
     corpse
    0.09
    Enemy
    0.09
     minecraft
    0.09
    Activations Density 0.042%

    No Known Activations