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. 76068
    Prev
    Next
    INDEX
    Explanations

    quantum cryptography

    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
     preferences
    -0.08
    'intérieur
    -0.08
    ícia
    -0.08
     nore
    -0.08
    Capabilities
    -0.08
    Preferences
    -0.07
     lob
    -0.07
     कायम
    -0.07
    jection
    -0.07
    preferences
    -0.07
    POSITIVE LOGITS
    .Pull
    0.08
     Ct
    0.08
    ICEF
    0.08
    Mrs
    0.07
    Pocket
    0.07
    BTC
    0.07
    sz
    0.07
    /pages
    0.07
     tablespoons
    0.07
    θο
    0.07
    Activations Density 0.001%

    No Known Activations