Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112975
    Prev
    Next
    INDEX
    Explanations

    She

    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
    的
    -0.08
    ು
    -0.08
     unfold
    -0.08
    跨度
    -0.08
    迁
    -0.07
    某
    -0.07
    案
    -0.07
    ופים
    -0.07
    ირვ
    -0.07
    ?n
    -0.07
    POSITIVE LOGITS
    ANGLE
    0.08
    .SC
    0.08
     ഉപയോഗ
    0.08
     ANG
    0.08
    _stock
    0.08
    ിട്ടില്ല
    0.07
     ECU
    0.07
     STOCK
    0.07
    _tests
    0.07
     അടിസ്ഥാന
    0.07
    Activations Density 0.386%

    No Known Activations