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. 112870
    Prev
    Next
    INDEX
    Explanations

    Trigonometry and square roots

    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
     临
    -0.08
     tonic
    -0.08
    -Time
    -0.08
    责
    -0.08
     dirigido
    -0.08
     변화
    -0.08
    css
    -0.08
     Listening
    -0.07
     Prompt
    -0.07
     exe
    -0.07
    POSITIVE LOGITS
     naap
    0.09
    _API
    0.08
     NA
    0.08
    NA
    0.08
    /api
    0.07
    �
    0.07
     scroll
    0.07
    ー
    0.07
     anywhere
    0.07
     sable
    0.07
    Activations Density 0.004%

    No Known Activations