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. 59592
    Prev
    Next
    INDEX
    Explanations

    n

    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
    体系
    -0.10
     الممت
    -0.10
    NERS
    -0.09
    成立
    -0.09
     unwind
    -0.08
     painstaking
    -0.08
    thest
    -0.08
     thé
    -0.08
    覚
    -0.08
    EAR
    -0.08
    POSITIVE LOGITS
    Shows
    0.08
    insel
    0.07
    ivu
    0.07
    el
    0.07
     babo
    0.07
    -shot
    0.07
     हिं
    0.07
    _tiles
    0.07
    ffi
    0.07
     tiles
    0.07
    Activations Density 0.003%

    No Known Activations