© 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 EvalsExportsAPI 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. 21037
    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
     ymax
    -0.09
    ៅ
    -0.09
    万吨
    -0.09
     datatype
    -0.09
     variants
    -0.09
    겠다
    -0.09
    ukhulu
    -0.09
    xtype
    -0.08
    otud
    -0.08
    ovao
    -0.08
    POSITIVE LOGITS
     अध्ययन
    0.09
    _BASE
    0.08
    _INT
    0.08
     Egypt
    0.08
    १४
    0.07
     England
    0.07
     группа
    0.07
     बेस
    0.07
     India
    0.07
     молод
    0.07
    Activations Density 0.010%

    No Known Activations