© 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. 3-RESID-POST-AA
    11. 12794
    Prev
    Next
    INDEX
    Explanations

    说明

    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
     Bal
    -0.09
     sill
    -0.08
     billionaire
    -0.07
     fors
    -0.07
     performed
    -0.07
     ബാല
    -0.07
     overs
    -0.07
     zeit
    -0.07
     sta
    -0.07
     Regis
    -0.07
    POSITIVE LOGITS
    (cap
    0.07
    摸
    0.07
    fd
    0.07
    碼
    0.07
    Tape
    0.07
    124
    0.07
    ательная
    0.07
     HAS
    0.07
    售
    0.07
    Maria
    0.07
    Activations Density 0.003%

    No Known Activations