© 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. 20212
    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
     =
    -0.09
     טייל
    -0.09
     учеб
    -0.08
     ગ્રામ
    -0.08
     ग्राम
    -0.08
    aksanaan
    -0.08
     educational
    -0.08
    徒
    -0.08
     части
    -0.08
     пределах
    -0.08
    POSITIVE LOGITS
    办公室
    0.15
     kantoor
    0.13
     sitzen
    0.13
     offices
    0.13
     कार्यालय
    0.12
     sitzt
    0.11
     Offices
    0.11
     escritório
    0.11
    办公
    0.11
     desks
    0.11
    Activations Density 0.019%

    No Known Activations