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. 111453
    Prev
    Next
    INDEX
    Explanations

    fractions

    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
    그
    -0.08
    배송
    -0.08
     gehören
    -0.08
    그리고
    -0.08
    presence
    -0.07
    متع
    -0.07
     उल्ल
    -0.07
    納
    -0.07
    attendance
    -0.07
    /the
    -0.07
    POSITIVE LOGITS
     depo
    0.08
     Hace
    0.08
    atoires
    0.08
     Ry
    0.08
     Strap
    0.07
    igor
    0.07
     Konto
    0.07
     gear
    0.07
     Yap
    0.07
     decay
    0.07
    Activations Density 0.003%

    No Known Activations