© 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. 110163
    Prev
    Next
    INDEX
    Explanations

    math variables

    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
     There
    -0.08
    וך
    -0.07
     כס
    -0.07
     Foundation
    -0.07
     Tengo
    -0.07
     விச
    -0.07
    ظهر
    -0.07
     Have
    -0.07
    риф
    -0.07
     Dropbox
    -0.07
    POSITIVE LOGITS
     odnosno
    0.09
    p
    0.08
    692
    0.08
    peated
    0.08
     czyli
    0.08
     yani
    0.08
    UNIC
    0.08
    つまり
    0.08
     यानी
    0.08
    univers
    0.08
    Activations Density 0.062%

    No Known Activations