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. 53487
    Prev
    Next
    INDEX
    Explanations

    zione

    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
    marshal
    -0.08
     accesses
    -0.07
    harm
    -0.07
    дерінің
    -0.07
    도가
    -0.07
    도를
    -0.07
     odors
    -0.07
    真的
    -0.07
     identifies
    -0.07
    -0.07
    POSITIVE LOGITS
     garanti
    0.08
     Gabri
    0.08
     задан
    0.08
     Philly
    0.08
     пунк
    0.08
     ditu
    0.07
     готовы
    0.07
     creemos
    0.07
     grem
    0.07
     Cabe
    0.07
    Activations Density 0.000%

    No Known Activations