© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 108480
    Prev
    Next
    INDEX
    Explanations

    Streets of Rage

    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
     অনুষ্ঠান
    -0.09
     cerim
    -0.09
     ceremonia
    -0.08
     cérémonie
    -0.08
    _algo
    -0.08
     পরিব
    -0.08
    cache
    -0.07
     conferencia
    -0.07
    _cache
    -0.07
     frivol
    -0.07
    POSITIVE LOGITS
     erat
    0.09
     smok
    0.08
     gears
    0.08
     Beng
    0.08
     Ved
    0.08
     pumping
    0.08
     bassist
    0.08
     rpm
    0.07
     asking
    0.07
    betal
    0.07
    Activations Density 0.002%

    No Known Activations