© 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. 51533
    Prev
    Next
    INDEX
    Explanations

    =

    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
     поставить
    -0.09
    ^^↵↵
    -0.09
     incentivar
    -0.08
    _SHORT
    -0.08
    Second
    -0.08
    सु
    -0.08
     reducido
    -0.08
    िष्ट
    -0.08
    せ
    -0.08
    ूरत
    -0.08
    POSITIVE LOGITS
     sering
    0.08
    unin
    0.08
     malos
    0.08
    fond
    0.08
     dik
    0.08
     pach
    0.08
     ganancias
    0.08
     ক্ষেত
    0.08
    (sum
    0.08
    ();↵↵↵↵
    0.07
    Activations Density 0.027%

    No Known Activations