© 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. 78355
    Prev
    Next
    INDEX
    Explanations

    African American hair

    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
     Maven
    -0.09
     atract
    -0.08
    ډ
    -0.08
     Ted
    -0.08
     launch
    -0.08
     MSc
    -0.08
    ټو
    -0.08
     Scrum
    -0.08
    Ted
    -0.07
     کمی
    -0.07
    POSITIVE LOGITS
     peril
    0.09
     Historically
    0.09
     Benjamin
    0.08
    Benjamin
    0.08
     histor
    0.07
     histori
    0.07
    akin
    0.07
     historically
    0.07
     evolving
    0.07
     réve
    0.07
    Activations Density 0.036%

    No Known Activations