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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 77126
    Prev
    Next
    INDEX
    Explanations

    house

    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
    ы
    -0.08
     ribbons
    -0.07
     Trudeau
    -0.07
    ущий
    -0.07
     Ribbon
    -0.07
    prob
    -0.07
     dak
    -0.07
    Turbo
    -0.07
    524
    -0.07
     fluff
    -0.07
    POSITIVE LOGITS
    装修
    0.09
     ACM
    0.08
    grown
    0.08
     Franc
    0.08
    wares
    0.08
    园
    0.08
     Soci
    0.08
    hold
    0.08
     diffuse
    0.08
     lign
    0.08
    Activations Density 0.039%

    No Known Activations