Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43401
    Prev
    Next
    INDEX
    Explanations

    Quote character

    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
     apparel
    -0.09
    半
    -0.08
    opp
    -0.08
     armor
    -0.07
    判断
    -0.07
    足
    -0.07
     carbide
    -0.07
     plana
    -0.07
     largely
    -0.07
     aircraft
    -0.07
    POSITIVE LOGITS
    Guardar
    0.08
    څ
    0.08
    नगर
    0.08
     imyaka
    0.08
     tic
    0.08
    EXEC
    0.08
    ixen
    0.08
     जरूर
    0.08
    Save
    0.07
     hailed
    0.07
    Activations Density 0.002%

    No Known Activations