© 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. 19371
    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
    .ศ
    -0.09
     több
    -0.09
    ाद
    -0.08
     תוך
    -0.08
     flere
    -0.08
    жащ
    -0.08
     όσ
    -0.08
    -0.08
    משך
    -0.08
    ाठ
    -0.08
    POSITIVE LOGITS
     заранее
    0.08
    UNA
    0.08
    ası
    0.08
     diet
    0.07
     możemy
    0.07
     предвар
    0.07
    !...
    0.07
    obi
    0.07
    Sometimes
    0.07
    aliro
    0.07
    Activations Density 0.001%
    No Known Activations