© 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 EvalsExportsinterp-engineNEWAPI 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. 22396
    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
     totiž
    -0.08
     zudem
    -0.08
    ीत
    -0.08
     semper
    -0.07
     Zudem
    -0.07
     chuyên
    -0.07
    ních
    -0.07
    née
    -0.07
    ús
    -0.07
     dessutom
    -0.07
    POSITIVE LOGITS
     શું
    0.19
     എന്ത
    0.18
    是什么
    0.18
     ఏమ
    0.18
    是多少
    0.18
    是多少钱
    0.17
     ڇا
    0.17
    是哪
    0.16
     چیست
    0.16
     ماذا
    0.16
    Activations Density 0.067%

    No Known Activations