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. 56057
    Prev
    Next
    INDEX
    Explanations

    empty calories and drinks

    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
    לה
    -0.09
    ampuan
    -0.08
     دغ
    -0.08
     intimidated
    -0.08
     amach
    -0.08
    ploit
    -0.08
     conclusão
    -0.07
     başarı
    -0.07
     aman
    -0.07
     सप्त
    -0.07
    POSITIVE LOGITS
     sugary
    0.10
     CORE
    0.08
     calorie
    0.08
     beverages
    0.08
     Poor
    0.08
     poor
    0.08
     Louisiana
    0.08
     conversion
    0.08
     nagu
    0.08
     adds
    0.08
    Activations Density 0.010%

    No Known Activations