© 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. 71615
    Prev
    Next
    INDEX
    Explanations

    Windows executables and DLLs

    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
    UNIT
    -0.07
    /cal
    -0.07
     tapes
    -0.07
     day's
    -0.07
     émission
    -0.07
    িকা
    -0.07
     pale
    -0.07
     cradle
    -0.07
    释
    -0.07
     scratch
    -0.07
    POSITIVE LOGITS
     Surf
    0.09
     Richter
    0.09
     Quem
    0.09
     Sorry
    0.08
     Outs
    0.08
     nötig
    0.07
     Sid
    0.07
     إجراء
    0.07
     líder
    0.07
     Gerä
    0.07
    Activations Density 0.002%

    No Known Activations