© 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. 19606
    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
    akaroon
    -0.09
    awule
    -0.08
    แข่งขัน
    -0.08
    력을
    -0.08
    ਼
    -0.07
    කි
    -0.07
     hierdie
    -0.07
    ährigen
    -0.07
    ärt
    -0.07
     while
    -0.07
    POSITIVE LOGITS
    て
    0.10
    ৃত
    0.10
    ্ত
    0.10
    pụtara
    0.09
    marked
    0.09
    cidas
    0.09
    шается
    0.09
    posed
    0.09
    шего
    0.09
    ্তা
    0.09
    Activations Density 0.002%

    No Known Activations