© 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. 7-RESID-POST-AA
    11. 1398
    Prev
    Next
    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /she
    -0.08
    light
    -0.07
     Yale
    -0.07
     enlightened
    -0.07
    _D
    -0.07
     reliably
    -0.07
    unc
    -0.07
    oguć
    -0.07
    ുവ
    -0.07
     appropr
    -0.07
    POSITIVE LOGITS
     كت
    0.08
    ↵↵//
    0.08
     કો�
    0.08
    రవ
    0.08
     radiator
    0.08
    तिक
    0.07
    іл
    0.07
    ↵                ↵
    0.07
     στιγ
    0.07
     spor
    0.07
    Activations Density 0.003%

    No Known Activations