© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 21234
    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
    �麟
    -0.09
     տեղի
    -0.09
     մասին
    -0.09
     Օ
    -0.09
    lements
    -0.09
     შესახებ
    -0.09
     இடம்பெ
    -0.08
    �ე
    -0.08
     แล้ว
    -0.08
     ხდება
    -0.08
    POSITIVE LOGITS
    学历
    0.11
     abilities
    0.10
     achie
    0.10
    Achievement
    0.09
     Achievement
    0.09
     intention
    0.09
     intentions
    0.09
     talented
    0.09
     affluent
    0.09
     achievements
    0.09
    Activations Density 0.006%

    No Known Activations