© 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. 129466
    Prev
    Next
    INDEX
    Explanations

    code characters

    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
     ஆகிய
    -0.09
    ombs
    -0.09
     இத
    -0.09
    reed
    -0.08
     lainnya
    -0.07
    acters
    -0.07
     その他
    -0.07
     conquista
    -0.07
    Reporting
    -0.07
     chiar
    -0.07
    POSITIVE LOGITS
    大家
    0.09
     TP
    0.08
     tinc
    0.07
    ான்
    0.07
    animation
    0.07
     Tale
    0.07
     Sik
    0.07
     Hig
    0.07
    cü
    0.07
    TODO
    0.07
    Activations Density 0.020%

    No Known Activations