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

    Neuronpedia

    Jacobian LensNEW
    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. 113387
    Prev
    Next
    INDEX
    Explanations

    winner

    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
     bo
    -0.08
    -0.08
    夜夜
    -0.08
    ibbean
    -0.07
     أحدث
    -0.07
    бах
    -0.07
    -0.07
     боль
    -0.07
    bor
    -0.07
     verði
    -0.07
    POSITIVE LOGITS
     ABD
    0.09
    ेता
    0.09
    ‍സ്
    0.08
     谁
    0.08
     endgült
    0.08
    �
    0.08
    确定
    0.08
    谁
    0.08
    此次
    0.08
     winner
    0.08
    Activations Density 0.017%
    No Known Activations