© 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. 109865
    Prev
    Next
    INDEX
    Explanations

    key

    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
    ോട്
    -0.08
    Legacy
    -0.08
    Ey
    -0.07
    CBS
    -0.07
     sab
    -0.07
     propias
    -0.07
     ontwikk
    -0.07
    Fan
    -0.07
    legacy
    -0.07
     съ
    -0.07
    POSITIVE LOGITS
     बनने
    0.08
     arre
    0.07
     GUID
    0.07
    itare
    0.07
     중심
    0.07
     Beyond
    0.07
     pek
    0.07
     Selain
    0.07
     каждому
    0.07
    ಿಟ
    0.07
    Activations Density 0.000%

    No Known Activations