© 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. 30929
    Prev
    Next
    INDEX
    Explanations

    migrate

    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
     dans
    -0.07
    дын
    -0.07
    文学
    -0.07
    汽车
    -0.07
     Petrol
    -0.07
     Malay
    -0.07
     выступ
    -0.07
    执
    -0.07
     Lon
    -0.07
     Veg
    -0.07
    POSITIVE LOGITS
    Tal
    0.08
    換
    0.08
     тра
    0.08
     Delegate
    0.08
     comfortably
    0.08
    DSM
    0.07
    Caso
    0.07
     Brid
    0.07
     giao
    0.07
    /on
    0.07
    Activations Density 0.003%

    No Known Activations