© 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. 31071
    Prev
    Next
    INDEX
    Explanations

    Business/Sales

    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
     aumentado
    -0.08
     abar
    -0.08
     analyzing
    -0.08
    ায
    -0.08
    omitempty
    -0.08
     examining
    -0.07
    لون
    -0.07
     examines
    -0.07
    _Error
    -0.07
     formación
    -0.07
    POSITIVE LOGITS
    素材
    0.09
     donating
    0.09
    願
    0.09
     seller
    0.09
     exporter
    0.09
     relinqu
    0.09
     부탁
    0.09
    跑路
    0.09
    เจ้
    0.09
    jual
    0.09
    Activations Density 0.135%

    No Known Activations