© 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. 19-RESID-POST-AA
    11. 18058
    Prev
    Next
    INDEX
    Explanations

    Slavic languages

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ებლად
    -0.11
    ნობ
    -0.10
    იურად
    -0.10
    ობრივ
    -0.10
    ողական
    -0.09
    մամբ
    -0.09
    ებლის
    -0.09
    очную
    -0.09
    יבית
    -0.09
    ционная
    -0.09
    POSITIVE LOGITS
    ые
    0.21
    ое
    0.20
    ого
    0.19
    ая
    0.19
    ый
    0.18
    ्या
    0.18
    ых
    0.17
    ой
    0.17
    ыми
    0.17
    ую
    0.17
    Activations Density 0.056%

    No Known Activations