© 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. 31034
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
     EMP
    -0.08
    EMP
    -0.08
     thrilled
    -0.07
     qi
    -0.07
    MO
    -0.07
    tia
    -0.07
    aalada
    -0.07
    IDS
    -0.07
    qi
    -0.07
     Sachen
    -0.07
    POSITIVE LOGITS
    且
    0.10
    ，因此
    0.10
    ，有
    0.09
    ，而
    0.09
    ，也
    0.09
    ，同时
    0.09
    ，为
    0.09
    、有
    0.08
     anomal
    0.08
    ，
    0.08
    Activations Density 0.039%

    No Known Activations