© 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. 23-RESID-POST-AA
    11. 52303
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ences/ence"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    amily
    -0.10
    ace
    -0.09
    ant
    -0.09
     defensive
    -0.08
    inite
    -0.08
    udier
    -0.08
    innu
    -0.08
    acial
    -0.08
     Defensive
    -0.08
    ader
    -0.08
    POSITIVE LOGITS
    ibilité
    0.10
    ències
    0.08
    EM
    0.08
    eren
    0.08
     résultat
    0.08
    IBILITY
    0.08
    ្ញ
    0.08
    성을
    0.08
    .Index
    0.07
     dishon
    0.07
    Activations Density 0.002%

    No Known Activations