© 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. 22388
    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
     taraf
    -0.08
     كۆر
    -0.08
    alsy
    -0.08
    unk
    -0.08
    garan
    -0.08
    -0.08
    -anak
    -0.08
    тай
    -0.08
    靠谱
    -0.08
    াদের
    -0.08
    POSITIVE LOGITS
     प्रश्न
    0.14
     सवाल
    0.14
    質問
    0.14
     flourish
    0.14
     rhetorical
    0.13
    ถาม
    0.13
     questions
    0.13
     Questions
    0.13
    _question
    0.13
    _questions
    0.13
    Activations Density 0.002%
    No Known Activations