© 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. 18161
    Prev
    Next
    INDEX
    Explanations

    en

    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
     Faʻ
    -0.09
    -uile
    -0.09
    ング
    -0.09
     Многие
    -0.09
     Аха
    -0.08
    -магаз
    -0.08
    -ию
    -0.08
    -Петер
    -0.08
    ência
    -0.08
     Осы
    -0.08
    POSITIVE LOGITS
     la
    0.15
     el
    0.15
     función
    0.14
     los
    0.13
     tiempo
    0.13
     un
    0.13
     cuanto
    0.12
     este
    0.12
     una
    0.12
     conjunto
    0.12
    Activations Density 0.012%

    No Known Activations