© 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. 109896
    Prev
    Next
    INDEX
    Explanations

    contradictions

    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
     fortunate
    -0.09
     transmis
    -0.08
     utilizes
    -0.08
     lu
    -0.07
     rut
    -0.07
    Lu
    -0.07
    rut
    -0.07
     используется
    -0.07
     রয়েছে
    -0.07
     convi
    -0.07
    POSITIVE LOGITS
     impossible
    0.09
     inconsistent
    0.09
     zomaar
    0.09
     unreasonable
    0.09
    太
    0.09
     endless
    0.09
     suddenly
    0.08
     infinitely
    0.08
     indefinitely
    0.08
    too
    0.08
    Activations Density 0.060%

    No Known Activations