© 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. 78342
    Prev
    Next
    INDEX
    Explanations

    club

    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
    来源
    -0.08
    ిస్త
    -0.08
    امة
    -0.08
    ిస్తుంది
    -0.08
    اريخ
    -0.08
     prophet
    -0.08
     elde
    -0.08
     снима
    -0.07
     originated
    -0.07
     históricos
    -0.07
    POSITIVE LOGITS
     TAP
    0.08
    avat
    0.08
     دوستان
    0.08
    rate
    0.08
     exploration
    0.07
     Ging
    0.07
    xing
    0.07
    etz
    0.07
    _TRA
    0.07
     Sakura
    0.07
    Activations Density 0.005%

    No Known Activations