© 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. 19-RESID-POST-AA
    11. 22755
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     World
    -0.08
     more
    -0.08
     testing
    -0.08
     maximum
    -0.08
     mais
    -0.07
     ingang
    -0.07
     Sunset
    -0.07
     વધુ
    -0.07
     leukste
    -0.07
    ’où
    -0.07
    POSITIVE LOGITS
    numerusform
    0.14
    text
    0.10
    textarea
    0.10
    bold
    0.10
    small
    0.10
    could
    0.09
    both
    0.09
    ensure
    0.09
    same
    0.09
    ponses
    0.09
    Activations Density 0.011%

    No Known Activations