© 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 EvalsExportsinterp-engineNEWAPI 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. 110320
    Prev
    Next
    INDEX
    Explanations

    connectors

    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
    -supported
    -0.09
     remarqu
    -0.08
     hierbij
    -0.07
     neigh
    -0.07
     puisqu
    -0.07
     compliment
    -0.07
     arreg
    -0.07
     Supported
    -0.07
     survives
    -0.07
     ఆయన
    -0.07
    POSITIVE LOGITS
     undue
    0.12
     unnecessarily
    0.11
     demasi
    0.11
     excessive
    0.11
    too
    0.11
     слишком
    0.10
     unnecessary
    0.10
    Too
    0.10
     premature
    0.10
     too
    0.10
    Activations Density 0.057%

    No Known Activations