© 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. 11-RESID-POST-AA
    11. 42991
    Prev
    Next
    INDEX
    Explanations

    functions

    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
     Michelin
    -0.08
     drones
    -0.08
    goods
    -0.08
    aghan
    -0.07
     evacu
    -0.07
     modalidades
    -0.07
     maquinaria
    -0.07
     evacuated
    -0.07
     stranded
    -0.07
     độ
    -0.07
    POSITIVE LOGITS
     ajouté
    0.09
     snippet
    0.08
     additions
    0.08
     hinzu
    0.08
     ઉમ
    0.08
    Adds
    0.08
     vintage
    0.08
     remembrance
    0.08
     amendments
    0.08
     لتح
    0.08
    Activations Density 0.006%

    No Known Activations