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. 42100
    Prev
    Next
    INDEX
    Explanations

    comma, by

    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
     coerc
    -0.09
     coer
    -0.08
     anatomical
    -0.08
     replica
    -0.08
    keyboard
    -0.07
     torture
    -0.07
    算盘
    -0.07
     sten
    -0.07
     anatom
    -0.07
    _spell
    -0.07
    POSITIVE LOGITS
     recientes
    0.16
     最新
    0.16
     recentes
    0.15
    ล่าสุด
    0.15
    _recent
    0.15
     terbaru
    0.15
     తాజ
    0.15
    Latest
    0.15
     reciente
    0.15
     最近
    0.14
    Activations Density 0.048%

    No Known Activations