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. 90470
    Prev
    Next
    INDEX
    Explanations

    books and reading

    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
     gbe
    -0.09
     centimeter
    -0.08
     clk
    -0.08
    冻结
    -0.08
     alcal
    -0.08
    gema
    -0.08
     col
    -0.08
     платы
    -0.08
     estamp
    -0.07
     technicians
    -0.07
    POSITIVE LOGITS
     фильмы
    0.15
     الكتب
    0.14
    /books
    0.14
     సినిమ
    0.13
     Goodreads
    0.12
     પુસ્ત
    0.12
    一本
    0.12
    genre
    0.12
     സിനിമ
    0.12
     Books
    0.12
    Activations Density 0.157%

    No Known Activations