© 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. 20550
    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
    低
    -0.14
     منخفض
    -0.13
     rendah
    -0.13
     lowest
    -0.13
     düşük
    -0.13
     Low
    -0.13
     smallest
    -0.13
     goedkope
    -0.13
    Low
    -0.13
     төмен
    -0.13
    POSITIVE LOGITS
     максим
    0.34
     maximum
    0.34
    _max
    0.32
     max
    0.31
    最大
    0.31
     maxima
    0.31
    max
    0.30
     最大
    0.30
     maximizing
    0.30
    .max
    0.29
    Activations Density 0.129%

    No Known Activations