© 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. 95286
    Prev
    Next
    INDEX
    Explanations

    embodied

    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
     fila
    -0.08
     berätt
    -0.08
     probing
    -0.08
    ellipse
    -0.08
     efter
    -0.08
     индекс
    -0.07
     bera
    -0.07
     joué
    -0.07
     afstand
    -0.07
    .database
    -0.07
    POSITIVE LOGITS
     Sap
    0.08
    _closed
    0.07
     Last
    0.07
    inut
    0.07
     విన
    0.07
    ทอง
    0.07
    utano
    0.07
     antique
    0.07
     മത
    0.07
    TW
    0.07
    Activations Density 0.001%

    No Known Activations