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. 60843
    Prev
    Next
    INDEX
    Explanations

    app development guides

    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
     temperament
    -0.10
     Nietzsche
    -0.09
     USSR
    -0.09
    (EXIT
    -0.08
     conceded
    -0.08
    .socket
    -0.08
    Destructor
    -0.08
     destructor
    -0.08
     bahan
    -0.08
     Doggy
    -0.08
    POSITIVE LOGITS
    .azure
    0.14
    .microsoft
    0.13
    Azure
    0.12
     Microsoft
    0.12
    Microsoft
    0.12
     Azure
    0.12
    微软
    0.11
     microsoft
    0.11
    .Azure
    0.11
    icrosoft
    0.10
    Activations Density 0.042%

    No Known Activations