© 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. 19839
    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
     approximately
    -0.12
     roughly
    -0.12
     aproximadamente
    -0.12
     Approximately
    -0.12
     yaklaşık
    -0.11
    Approximately
    -0.11
     приблиз
    -0.10
    approximately
    -0.10
     approx
    -0.10
     लगभग
    -0.10
    POSITIVE LOGITS
    either
    0.15
     either
    0.14
     esimerkiksi
    0.14
     various
    0.13
     είτε
    0.13
     joko
    0.12
     commonly
    0.12
    Either
    0.12
     bijvoorbeeld
    0.12
    Various
    0.12
    Activations Density 0.037%

    No Known Activations