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. 117512
    Prev
    Next
    INDEX
    Explanations

    code

    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
    sas
    -0.08
     ironically
    -0.08
     inflicted
    -0.08
    yeen
    -0.08
     psychologically
    -0.08
    uded
    -0.07
    吞
    -0.07
     attracted
    -0.07
    vamos
    -0.07
    Sid
    -0.07
    POSITIVE LOGITS
     _)
    0.09
     ...)
    0.08
     paut
    0.08
     영
    0.08
     espécies
    0.08
     {})
    0.07
     varargin
    0.07
    ...)
    0.07
    ){
    ↵
    0.07
     perspectives
    0.07
    Activations Density 0.010%

    No Known Activations