Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 60745
    Prev
    Next
    INDEX
    Explanations

    game code particles/coordinates

    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
     evolved
    -0.08
     elected
    -0.08
    rnd
    -0.07
     elections
    -0.07
    690
    -0.07
    celle
    -0.07
    íl
    -0.07
    taire
    -0.07
     eleições
    -0.07
     evolution
    -0.07
    POSITIVE LOGITS
    OURCES
    0.09
     Temporary
    0.09
    Temporary
    0.08
     temporary
    0.08
    ساس
    0.08
     provisional
    0.08
    .Temp
    0.08
     Tattoos
    0.08
    ermanent
    0.08
    .temp
    0.07
    Activations Density 0.001%

    No Known Activations