© 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. 109867
    Prev
    Next
    INDEX
    Explanations

    pair

    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
    Negative Logits
    력
    -0.08
    ادة
    -0.08
    éral
    -0.08
    flammatory
    -0.08
     cloak
    -0.08
    streeks
    -0.07
     hidden
    -0.07
    áles
    -0.07
     сипат
    -0.07
     vart
    -0.07
    POSITIVE LOGITS
     Intelli
    0.08
     microbes
    0.08
    chappen
    0.08
     Indy
    0.08
     onboarding
    0.08
    Merge
    0.08
    -writing
    0.08
     provisioning
    0.08
     proofreading
    0.08
     inoc
    0.08
    Activations Density 0.001%

    No Known Activations