© 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. 19810
    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
    oraan
    -0.08
     those
    -0.08
     perfectamente
    -0.08
     arbitrary
    -0.08
     hark
    -0.07
    Anyone
    -0.07
     Як
    -0.07
     trebui
    -0.07
     сюда
    -0.07
     →
    -0.07
    POSITIVE LOGITS
    比較
    0.12
     comparing
    0.11
     Compare
    0.10
    比较
    0.10
     비교
    0.10
     Comparing
    0.10
     vergelijken
    0.10
     outwe
    0.10
     diferença
    0.10
    compare
    0.10
    Activations Density 0.007%

    No Known Activations