© 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. 129530
    Prev
    Next
    INDEX
    Explanations

    coordinate

    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
     LINK
    -0.08
     dai
    -0.08
    148
    -0.07
     malo
    -0.07
     Ram
    -0.07
     നിന്ന്
    -0.07
     dalle
    -0.07
     അംഗ
    -0.07
     Samm
    -0.07
     rast
    -0.07
    POSITIVE LOGITS
    纵
    0.08
     ней
    0.08
    ương
    0.07
    轴
    0.07
     сет
    0.07
    wealth
    0.07
     consortium
    0.07
    iн
    0.07
     Callable
    0.07
     sete
    0.07
    Activations Density 0.013%

    No Known Activations