© 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. 52098
    Prev
    Next
    INDEX
    Explanations

    Cossacks and Polish-Lithuanian Commonwealth

    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
    ’électricité
    -0.10
    Nimbus
    -0.09
    'électricité
    -0.08
     Eiffel
    -0.08
    viewport
    -0.08
     fútbol
    -0.08
    Infer
    -0.08
    ELE
    -0.08
    week
    -0.08
    ’w
    -0.08
    POSITIVE LOGITS
     Het
    0.12
     het
    0.11
     koz
    0.11
     Polish
    0.11
     C
    0.11
    Het
    0.09
     kur
    0.09
     Volunteer
    0.09
     Poland
    0.09
     polish
    0.09
    Activations Density 0.004%

    No Known Activations