© 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. 22758
    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
     asses
    -0.09
     reina
    -0.09
     könne
    -0.08
     medicijnen
    -0.08
     jas
    -0.08
     lahko
    -0.08
     pudesse
    -0.07
     graag
    -0.07
     Testing
    -0.07
     documenten
    -0.07
    POSITIVE LOGITS
    耗
    0.11
    量
    0.11
    否
    0.10
    ergy
    0.10
    allage
    0.09
    vironment
    0.09
    ERGY
    0.09
    ‍ഡ
    0.09
    quiry
    0.09
    nergy
    0.09
    Activations Density 0.001%

    No Known Activations