© 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. 19234
    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
     مرحلة
    -0.09
     plead
    -0.09
     levou
    -0.08
    rophy
    -0.08
     coached
    -0.08
    beiten
    -0.08
     المرحلة
    -0.08
     hoş
    -0.08
     dressed
    -0.08
    زيز
    -0.08
    POSITIVE LOGITS
    ISBN
    0.17
     ISBN
    0.16
    号码
    0.15
     isbn
    0.14
    isbn
    0.14
     ಸಂಖ್ಯೆ
    0.13
    番号
    0.12
    978
    0.12
     numbers
    0.12
     ಸಂಖ್ಯ
    0.12
    Activations Density 0.011%

    No Known Activations