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. 58436
    Prev
    Next
    INDEX
    Explanations

    The

    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
     guesses
    -0.09
     уга
    -0.09
     guess
    -0.09
    guess
    -0.09
    Guess
    -0.09
    猜
    -0.08
     Guess
    -0.08
     guessing
    -0.08
     aparentemente
    -0.08
    Miss
    -0.07
    POSITIVE LOGITS
     déta
    0.10
     исследования
    0.09
     detaill
    0.09
     researched
    0.09
     подробно
    0.09
     histori
    0.09
    (topic
    0.08
     nonfiction
    0.08
     umfang
    0.08
    Topic
    0.08
    Activations Density 0.066%

    No Known Activations