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. 120374
    Prev
    Next
    INDEX
    Explanations

    retinopathy

    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
     deity
    -0.08
     Assembl
    -0.07
     puzzle
    -0.07
    uzzle
    -0.07
     tril
    -0.07
     предп
    -0.07
     Puzzle
    -0.07
    -0.07
    谜
    -0.07
     deuts
    -0.07
    POSITIVE LOGITS
     一级
    0.09
     qualifying
    0.08
     arrests
    0.08
    �
    0.08
     corrections
    0.08
    等级
    0.08
     screenshots
    0.08
     levels
    0.08
    .VISIBLE
    0.08
     screening
    0.08
    Activations Density 0.002%

    No Known Activations