© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 52290
    Prev
    Next
    INDEX
    Explanations

    incluir

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    \Input
    -0.08
    IPHER
    -0.08
    struct
    -0.08
    urra
    -0.07
     Stu
    -0.07
    ন্টার
    -0.07
     knee
    -0.07
     Hü
    -0.07
    ्ट्र
    -0.07
     ocurre
    -0.07
    POSITIVE LOGITS
    cluir
    0.17
    cl
    0.12
    CL
    0.10
    	cl
    0.10
    .cl
    0.10
    CLS
    0.09
    clude
    0.09
     क्ल
    0.09
     ಕ್ಲ
    0.09
    clud
    0.08
    Activations Density 0.001%

    No Known Activations