© 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. 11-RESID-POST-AA
    11. 71490
    Prev
    Next
    INDEX
    Explanations

    knowledge distillation

    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
    chair
    -0.09
    terior
    -0.08
    estellt
    -0.08
    ētu
    -0.08
    ikele
    -0.08
     cutters
    -0.08
     Political
    -0.08
    cular
    -0.08
    metik
    -0.08
    ూప
    -0.07
    POSITIVE LOGITS
     golden
    0.09
    694
    0.08
     comparison
    0.08
    /k
    0.08
    Golden
    0.08
     insists
    0.08
     bath
    0.08
    Creation
    0.08
     synchronization
    0.07
     Golden
    0.07
    Activations Density 0.002%

    No Known Activations