© 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. 71577
    Prev
    Next
    INDEX
    Explanations

    template

    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
     regenerated
    -0.09
    Borders
    -0.08
    .Record
    -0.08
    cep
    -0.08
    ξε
    -0.08
     gelernt
    -0.08
     નિયમ
    -0.08
     નિર્ણ
    -0.08
    тически
    -0.08
    _RESULTS
    -0.08
    POSITIVE LOGITS
    rd
    0.09
     options
    0.08
     інт
    0.08
    igem
    0.08
    èm
    0.07
     Smoking
    0.07
    options
    0.07
     girl
    0.07
     smoking
    0.07
     numeros
    0.07
    Activations Density 0.001%

    No Known Activations