© 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. 22737
    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
     πολι
    -0.09
     �
    -0.09
     terrorismo
    -0.09
     terrorism
    -0.09
     terrorist
    -0.08
     vandal
    -0.08
     നഗ
    -0.08
     քաղաքի
    -0.08
    лай
    -0.08
    Scanner
    -0.08
    POSITIVE LOGITS
     herbs
    0.17
     herbal
    0.15
     Herbs
    0.15
     Ayur
    0.14
     Herbal
    0.14
     nourishing
    0.13
     medicines
    0.13
    药
    0.13
     Ayurveda
    0.13
     medicine
    0.12
    Activations Density 0.009%

    No Known Activations