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. 90262
    Prev
    Next
    INDEX
    Explanations

    as

    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
    -sol
    -0.08
    Solve
    -0.08
    normally
    -0.08
     решил
    -0.08
     cooperate
    -0.08
    Ken
    -0.08
     withdrawing
    -0.08
    Wid
    -0.07
     от
    -0.07
    Kun
    -0.07
    POSITIVE LOGITS
     Ä
    0.08
     Lakes
    0.07
     glove
    0.07
     Rainbow
    0.07
    ,!
    0.07
     së
    0.07
     Containers
    0.07
     Anniversary
    0.07
     road
    0.07
     gloves
    0.07
    Activations Density 0.003%

    No Known Activations