© 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. 30076
    Prev
    Next
    INDEX
    Explanations

    5

    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
    остей
    -0.09
     invol
    -0.09
     divulgado
    -0.08
    impi
    -0.08
    যুক্ত
    -0.08
     dismiss
    -0.08
     indeb
    -0.08
    lectic
    -0.08
     معاملات
    -0.08
     vyst
    -0.08
    POSITIVE LOGITS
    विश्व
    0.08
    _LAST
    0.08
    _NE
    0.08
    _MIN
    0.08
    Jag
    0.08
    _ALL
    0.08
    _ACCEL
    0.08
    aught
    0.07
    _CMD
    0.07
    _TYPES
    0.07
    Activations Density 0.006%

    No Known Activations