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. 459
    Prev
    Next
    INDEX
    Explanations

    math with integers

    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
    _PENDING
    -0.08
    ห
    -0.08
    ม
    -0.08
     mars
    -0.07
    building
    -0.07
    _Params
    -0.07
     Sea
    -0.07
    hek
    -0.07
    QR
    -0.07
     Lon
    -0.07
    POSITIVE LOGITS
    Trig
    0.08
     kane
    0.07
     CBS
    0.07
    CBS
    0.07
     traveled
    0.07
     Aux
    0.07
    락
    0.07
    Gateway
    0.07
     raha
    0.07
    Collector
    0.07
    Activations Density 0.129%

    No Known Activations