Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12625
    Prev
    Next
    INDEX
    Explanations

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    837
    -0.09
     ka
    -0.08
    Habit
    -0.08
     Presid
    -0.08
     diamond
    -0.07
     sér
    -0.07
     detr
    -0.07
    838
    -0.07
     Diamond
    -0.07
    -0.07
    POSITIVE LOGITS
    alyzed
    0.08
    ndata
    0.08
     qul
    0.08
    nus
    0.07
    ীয়
    0.07
     contenus
    0.07
    பெ
    0.07
    liegenden
    0.07
    ীয়
    0.07
    they
    0.07
    Activations Density 0.002%

    No Known Activations