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. 11908
    Prev
    Next
    INDEX
    Explanations

    ocker

    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
    zing
    -0.08
    378
    -0.08
    fiya
    -0.08
    viral
    -0.07
    gas
    -0.07
    _Open
    -0.07
    ز
    -0.07
    gum
    -0.07
    kep
    -0.07
    yay
    -0.07
    POSITIVE LOGITS
     uren
    0.10
     Firenze
    0.08
    秋
    0.08
     downstairs
    0.08
     groß
    0.08
     roses
    0.08
     Besch
    0.07
     trá
    0.07
    ámara
    0.07
     Coming
    0.07
    Activations Density 0.000%

    No Known Activations