© 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. 20882
    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
     vermutlich
    -0.12
    ，每
    -0.11
     wahrscheinlich
    -0.11
     probablement
    -0.11
     probablemente
    -0.11
     sicherlich
    -0.10
     cualquier
    -0.10
    ，在
    -0.10
     waarschijnlijk
    -0.10
     provavelmente
    -0.10
    POSITIVE LOGITS
     could
    0.20
    Could
    0.17
     pourraient
    0.17
     Could
    0.17
    could
    0.17
     pourrait
    0.17
     might
    0.17
     voisi
    0.16
     would
    0.16
     podrían
    0.16
    Activations Density 0.028%

    No Known Activations