© 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. 18032
    Prev
    Next
    INDEX
    Explanations

    say flavor

    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
    制度
    -0.09
    公益
    -0.09
     stric
    -0.08
     inefficient
    -0.08
    CGRect
    -0.08
     sociales
    -0.08
     previd
    -0.08
     freel
    -0.08
     olimp
    -0.08
    calloc
    -0.08
    POSITIVE LOGITS
     sabor
    0.32
     smaak
    0.32
     вку
    0.31
    味
    0.30
     sabores
    0.30
     स्वाद
    0.30
     flavor
    0.29
     Geschmack
    0.29
     smaken
    0.28
     맛
    0.28
    Activations Density 0.064%

    No Known Activations