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. 53434
    Prev
    Next
    INDEX
    Explanations

    包括

    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
    而言
    -0.08
    ord
    -0.08
    оруж
    -0.08
    ল্লেখ
    -0.08
    কে
    -0.07
    ীব
    -0.07
    guards
    -0.07
     GPUs
    -0.07
    ਮ
    -0.07
    anim
    -0.07
    POSITIVE LOGITS
     enclosed
    0.10
    -contained
    0.09
     italic
    0.09
    Contents
    0.09
     Contents
    0.09
    _contents
    0.09
     enclosing
    0.09
     सामग्री
    0.09
     contents
    0.09
    weeted
    0.09
    Activations Density 0.014%

    No Known Activations