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. 106215
    Prev
    Next
    INDEX
    Explanations

    Vitamins, beta-carotene

    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
     ker
    -0.08
     Ker
    -0.08
    Ker
    -0.08
     KPI
    -0.08
     الس
    -0.08
     Ninja
    -0.08
     stammen
    -0.08
     ASP
    -0.07
    Arrange
    -0.07
     Drive
    -0.07
    POSITIVE LOGITS
     Trials
    0.09
     equipo
    0.08
     trials
    0.08
     mod
    0.08
     futile
    0.08
    Trials
    0.08
     supplementation
    0.08
     controversial
    0.08
    .plugin
    0.08
    .enabled
    0.08
    Activations Density 0.010%

    No Known Activations