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. 46718
    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
    dsn
    -0.08
     활용
    -0.08
    pai
    -0.08
     이를
    -0.08
     discover
    -0.08
     ontdek
    -0.08
     அந்த
    -0.08
    .BASE
    -0.08
     ඒ
    -0.08
     항상
    -0.08
    POSITIVE LOGITS
     However
    0.10
    However
    0.09
     however
    0.09
     overshadow
    0.09
     jedoch
    0.09
    ,但是
    0.08
     হলেও
    0.08
     olsa
    0.08
    。然而
    0.08
    。しかし
    0.08
    Activations Density 0.017%

    No Known Activations