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. 43111
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
    ក្រ
    -0.08
     gospodar
    -0.08
    ”、
    -0.08
     thay
    -0.08
    ”、“
    -0.08
    เด็ก
    -0.08
     äußer
    -0.08
     overwhel
    -0.08
     Representatives
    -0.08
    :path
    -0.08
    POSITIVE LOGITS
    _exc
    0.07
    venta
    0.07
    Ws
    0.07
    Entre
    0.07
    invoice
    0.07
    ಟ್ಟ
    0.07
     greeting
    0.07
    Bonus
    0.07
     Bonus
    0.07
    Excel
    0.07
    Activations Density 0.086%

    No Known Activations