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. 43479
    Prev
    Next
    INDEX
    Explanations

    version/edition

    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
    mesine
    -0.09
    DOCTYPE
    -0.09
    digit
    -0.08
    masına
    -0.08
    ecn
    -0.08
     ster
    -0.08
    -worthy
    -0.08
     egiten
    -0.08
    ңа
    -0.08
    -ident
    -0.08
    POSITIVE LOGITS
     संस्करण
    0.10
     version
    0.09
    版
    0.09
     Arm
    0.09
     версия
    0.08
     edition
    0.08
     variante
    0.08
    .arm
    0.08
     arm
    0.08
    _ARM
    0.08
    Activations Density 0.031%

    No Known Activations