© 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. 47330
    Prev
    Next
    INDEX
    Explanations

    inside

    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
    지만
    -0.08
    Song
    -0.07
    Visualizer
    -0.07
    destination
    -0.07
    -0.07
    mania
    -0.07
    Expr
    -0.07
    printer
    -0.07
     Expr
    -0.07
    Да
    -0.07
    POSITIVE LOGITS
     tricky
    0.08
    र्तन
    0.08
     Craw
    0.08
     istifadə
    0.08
     Pä
    0.08
     Hert
    0.08
     Gibraltar
    0.08
     Behörden
    0.08
     CURL
    0.08
     Newspapers
    0.08
    Activations Density 0.007%
    No Known Activations