© 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. 17948
    Prev
    Next
    INDEX
    Explanations

    必

    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
     detecting
    -0.09
    aphezulu
    -0.08
    țin
    -0.08
    iselwa
    -0.08
     edildi
    -0.08
     ukuf
    -0.08
     adjusting
    -0.07
     થતાં
    -0.07
     બનાવવા
    -0.07
    елиться
    -0.07
    POSITIVE LOGITS
     camino
    0.12
     रास्त
    0.12
     caminhos
    0.12
     পথ
    0.12
     caminho
    0.12
     caminos
    0.12
     путь
    0.12
    路径
    0.12
     avenue
    0.12
     vías
    0.11
    Activations Density 0.001%

    No Known Activations