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. 44075
    Prev
    Next
    INDEX
    Explanations

    Computer security vulnerabilities

    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
     uro
    -0.08
    posite
    -0.08
    unehmen
    -0.08
    edded
    -0.08
     biy
    -0.08
     nějak
    -0.08
    porn
    -0.08
     Κυ
    -0.07
    _license
    -0.07
     السلام
    -0.07
    POSITIVE LOGITS
     Accountant
    0.08
     exploited
    0.08
     vulnerabilities
    0.08
     vulnerability
    0.08
    .a
    0.08
    Fon
    0.07
     Vulner
    0.07
     cloning
    0.07
    lover
    0.07
    系列
    0.07
    Activations Density 0.002%

    No Known Activations