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. 60850
    Prev
    Next
    INDEX
    Explanations

    inspire

    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
    وج
    -0.08
    overs
    -0.08
    တ
    -0.08
     अर्थात
    -0.07
     Bur
    -0.07
     pension
    -0.07
     Springer
    -0.07
     stump
    -0.07
     Schwarz
    -0.07
    .Resize
    -0.07
    POSITIVE LOGITS
    áló
    0.08
    deal
    0.08
     प्रेर
    0.08
     inspiration
    0.07
     انگی
    0.07
     impetus
    0.07
     vigor
    0.07
    áció
    0.07
    новения
    0.07
    iele
    0.07
    Activations Density 0.019%

    No Known Activations