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. 111781
    Prev
    Next
    INDEX
    Explanations

    check/see

    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
     Beginner
    -0.08
     પાર્ટ
    -0.08
     reportedly
    -0.08
    皆
    -0.08
     партия
    -0.07
    	part
    -0.07
     Bonnie
    -0.07
     KO
    -0.07
    ાત
    -0.07
    欲
    -0.07
    POSITIVE LOGITS
    一下
    0.10
     apakah
    0.09
     ukuze
    0.08
    有没有
    0.08
     понимать
    0.08
     beachten
    0.08
     siitä
    0.08
     umb
    0.08
    看看
    0.07
     tahu
    0.07
    Activations Density 0.072%

    No Known Activations