© 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. 18699
    Prev
    Next
    INDEX
    Explanations

    С

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '
    -0.09
     χρήση
    -0.08
     ‘
    -0.08
     (?)
    -0.08
    public
    -0.07
     использование
    -0.07
     direct
    -0.07
     defines
    -0.07
    CODE
    -0.07
     public
    -0.07
    POSITIVE LOGITS
     diýen
    0.10
    首先
    0.09
    ！！！
    0.09
    ！！↵
    0.09
     деді
    0.09
     ابتدا
    0.09
    טן
    0.09
    ujejo
    0.08
    ופא
    0.08
     trouvent
    0.08
    Activations Density 0.000%

    No Known Activations