Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 12959
    Prev
    Next
    INDEX
    Explanations

    Generating content

    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
    ,ll
    -0.08
     dragged
    -0.07
     Satin
    -0.07
     Laz
    -0.07
    Liked
    -0.07
    Trim
    -0.07
    -storage
    -0.07
     lubricant
    -0.07
     twitter
    -0.07
    -twitter
    -0.07
    POSITIVE LOGITS
     quizzes
    0.12
     экзам
    0.10
    考试
    0.10
    Quiz
    0.10
     امتح
    0.10
    難
    0.10
    difficulty
    0.10
     probing
    0.10
    quiz
    0.10
     quiz
    0.10
    Activations Density 0.039%

    No Known Activations