© 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. 109989
    Prev
    Next
    INDEX
    Explanations

    quotes/punctuation

    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
     counsel
    -0.08
     measures
    -0.08
     Counsel
    -0.07
     Deferred
    -0.07
     simplic
    -0.07
     Measures
    -0.07
    sein
    -0.07
    ukur
    -0.07
     artillery
    -0.07
     talked
    -0.07
    POSITIVE LOGITS
    abcdefghijklmnopqrstuvwxyz
    0.11
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    0.11
    abcdefghijkl
    0.10
    owels
    0.09
     문자열
    0.09
     목록
    0.09
     digits
    0.09
     переч
    0.09
    digits
    0.09
    _digits
    0.08
    Activations Density 0.007%

    No Known Activations