© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 79025
    Prev
    Next
    INDEX
    Explanations

    conduct

    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
     hålla
    -0.08
    zd
    -0.08
     juh
    -0.08
     מאד
    -0.08
     দিয়ে
    -0.08
    ್ಧ
    -0.08
     gyn
    -0.07
     bleaching
    -0.07
    ్ధ
    -0.07
     langzaam
    -0.07
    POSITIVE LOGITS
     scouts
    0.09
     kuz
    0.08
     alimentaire
    0.08
     submiss
    0.08
    ordial
    0.08
    /Footer
    0.08
     Fortnite
    0.08
     Kommentare
    0.08
     cookies
    0.07
    hedral
    0.07
    Activations Density 0.003%

    No Known Activations