© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 65551
    Prev
    Next
    INDEX
    Explanations

    voting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kı
    -0.09
     load
    -0.08
    Coordinator
    -0.07
    খ
    -0.07
    ನ್ನ
    -0.07
     beza
    -0.07
     letter
    -0.07
    ပ်
    -0.07
    Little
    -0.07
     Coordinator
    -0.07
    POSITIVE LOGITS
    批准
    0.14
     unanimously
    0.14
     aprobar
    0.13
     aprov
    0.13
     approvals
    0.13
     aprovação
    0.12
     approving
    0.12
     approval
    0.12
     Approval
    0.12
     aprobación
    0.11
    Activations Density 0.094%

    No Known Activations