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. 88090
    Prev
    Next
    INDEX
    Explanations

    Markdown image tag

    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
     SELL
    -0.09
    軍
    -0.08
     prote
    -0.08
     Navy
    -0.08
     Powers
    -0.08
     favorecer
    -0.08
    SELL
    -0.07
     Rocha
    -0.07
     favor
    -0.07
     Mille
    -0.07
    POSITIVE LOGITS
    =image
    0.11
    (image
    0.11
     depicts
    0.10
     jpg
    0.09
    Screenshot
    0.09
    (filename
    0.09
    _url
    0.09
     Screenshot
    0.09
    image
    0.09
     JPG
    0.09
    Activations Density 0.003%

    No Known Activations