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. 46668
    Prev
    Next
    INDEX
    Explanations

    void

    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
     pervers
    -0.09
     처음
    -0.08
     JFile
    -0.08
    =N
    -0.08
     süreç
    -0.08
     tamamen
    -0.08
    NSNotification
    -0.08
     depressed
    -0.07
     rechaz
    -0.07
    Прав
    -0.07
    POSITIVE LOGITS
    }`);↵
    0.09
    ostrar
    0.09
     Brewing
    0.08
     essential
    0.08
     /*<<<
    0.08
    cao
    0.08
     peso
    0.07
    'entretien
    0.07
    '];↵
    0.07
    .goto
    0.07
    Activations Density 0.003%

    No Known Activations