© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 64624
    Prev
    Next
    INDEX
    Explanations

    dependent

    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
    现场
    -0.08
    巴黎
    -0.08
     blower
    -0.08
    领取
    -0.07
     sweater
    -0.07
    authenticated
    -0.07
    必要
    -0.07
    遵
    -0.07
    同比
    -0.07
    真人
    -0.07
    POSITIVE LOGITS
     utama
    0.09
     principale
    0.08
    मुख
    0.08
    자리
    0.08
     ಸ್ಥಾನ
    0.08
    재
    0.08
    .Basic
    0.08
    ressor
    0.07
     отличие
    0.07
     dernier
    0.07
    Activations Density 0.004%

    No Known Activations