© 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. 75575
    Prev
    Next
    INDEX
    Explanations

    synth

    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
     英
    -0.08
     Chapel
    -0.08
    erweise
    -0.08
     exceeding
    -0.08
     expelled
    -0.07
     Flem
    -0.07
     strangers
    -0.07
     Arn
    -0.07
     chocolate
    -0.07
     רב
    -0.07
    POSITIVE LOGITS
     circuitry
    0.09
     malfunction
    0.09
    陷
    0.08
     dreamy
    0.08
     bass
    0.08
     futuristic
    0.08
    朋克
    0.08
     mal
    0.08
     Dreams
    0.08
     techno
    0.08
    Activations Density 0.003%

    No Known Activations