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. 77408
    Prev
    Next
    INDEX
    Explanations

    Math symbols

    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
     Ebola
    -0.08
     tears
    -0.08
    "]="
    -0.08
    rollable
    -0.08
    .walk
    -0.07
     être
    -0.07
     PLEASE
    -0.07
     الالت
    -0.07
    .dem
    -0.07
    ']="
    -0.07
    POSITIVE LOGITS
    Equation
    0.08
     paut
    0.08
    lope
    0.08
     impending
    0.07
     chu
    0.07
     জিল
    0.07
    ാങ്ങ
    0.07
    638
    0.07
     sudoku
    0.07
    Sud
    0.07
    Activations Density 0.016%

    No Known Activations