© 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. 23-RESID-POST-AA
    11. 96814
    Prev
    Next
    INDEX
    Explanations

    IE

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ürt
    -0.07
     discretionary
    -0.07
    raz
    -0.07
     chem
    -0.07
    atever
    -0.07
     المح
    -0.07
     خواهید
    -0.07
     trạng
    -0.07
    (Math
    -0.07
     Math
    -0.07
    POSITIVE LOGITS
     Auteur
    0.08
    Auteur
    0.08
    Vision
    0.08
     elo
    0.08
    Painter
    0.08
    _globals
    0.08
    森林
    0.08
    .genre
    0.08
    Factory
    0.08
    .firestore
    0.08
    Activations Density 0.001%

    No Known Activations