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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 55956
    Prev
    Next
    INDEX
    Explanations

    survival

    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
     позволяет
    -0.09
     hadir
    -0.08
     landfill
    -0.08
    _missing
    -0.08
     professionnels
    -0.08
    Missing
    -0.08
     Missing
    -0.08
     veta
    -0.07
     residente
    -0.07
     missing
    -0.07
    POSITIVE LOGITS
     doeleinden
    0.08
     prestige
    0.08
     Ż
    0.08
     Garcia
    0.08
    /title
    0.07
     المرج
    0.07
     വേണ്ടി
    0.07
    IRONMENT
    0.07
    ожд
    0.07
    cz
    0.07
    Activations Density 0.021%

    No Known Activations