© 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. 20693
    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
    utzutage
    -0.09
    _using
    -0.08
     gunakan
    -0.08
     utilisez
    -0.08
     nutzen
    -0.08
     utiliser
    -0.08
     gebruiken
    -0.08
     استفاده
    -0.08
    資訊
    -0.08
    маны
    -0.08
    POSITIVE LOGITS
     approval
    0.26
    批准
    0.25
    审批
    0.25
     aprobación
    0.24
    Approval
    0.24
     Approval
    0.23
     approvals
    0.23
     aprovação
    0.23
     승인
    0.22
    approval
    0.22
    Activations Density 0.065%

    No Known Activations