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. 43286
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     NOT
    -0.08
     Mac
    -0.08
    岁的
    -0.07
    祖
    -0.07
     CIM
    -0.07
    .meg
    -0.07
    工作的
    -0.07
    _VERTEX
    -0.07
    ämän
    -0.07
    Mac
    -0.07
    POSITIVE LOGITS
     też
    0.10
     тоже
    0.09
     depending
    0.08
    기도
    0.08
    Depending
    0.08
     thereof
    0.07
     등이
    0.07
    wirtschaft
    0.07
     washington
    0.07
     수도
    0.07
    Activations Density 0.194%

    No Known Activations