© 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. 23-RESID-POST-AA
    11. 50970
    Prev
    Next
    INDEX
    Explanations

    chronic

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rash
    -0.09
     visceral
    -0.08
     bloodstream
    -0.08
     wyg
    -0.08
    Toe
    -0.08
     ಮುಖ
    -0.08
     visor
    -0.08
     Toe
    -0.08
    臀
    -0.08
     tampon
    -0.08
    POSITIVE LOGITS
     chronic
    0.15
     Chronic
    0.14
     хроничес
    0.12
     χρόνια
    0.12
     chronique
    0.12
    COP
    0.11
    �
    0.11
     COPD
    0.10
     ქრ
    0.10
     Chron
    0.10
    Activations Density 0.007%

    No Known Activations