© 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. 22757
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ēļ
    -0.08
     exhibited
    -0.08
    ствует
    -0.08
    Поз
    -0.08
     במיוחד
    -0.08
    laşdır
    -0.07
    ğan
    -0.07
     abandoning
    -0.07
    ópez
    -0.07
    ouis
    -0.07
    POSITIVE LOGITS
    -hand
    0.13
     Gems
    0.12
    -Hand
    0.12
     hand
    0.11
    _HAND
    0.11
    Hand
    0.11
     gems
    0.10
     Hand
    0.10
    _hand
    0.10
     treasures
    0.10
    Activations Density 0.008%

    No Known Activations