© 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. 71812
    Prev
    Next
    INDEX
    Explanations

    30

    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
    _monitor
    -0.08
    _multiple
    -0.08
    multiple
    -0.08
    laut
    -0.08
    (Math
    -0.08
    _visual
    -0.07
    ૂત
    -0.07
    _TO
    -0.07
    Visual
    -0.07
    DOUBLE
    -0.07
    POSITIVE LOGITS
     qors
    0.08
     soil
    0.08
    0.08
     со
    0.07
     შენ
    0.07
     turmoil
    0.07
     rentrée
    0.07
     сегодняш
    0.07
     ranc
    0.07
     täglich
    0.07
    Activations Density 0.012%
    No Known Activations