© 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. 63155
    Prev
    Next
    INDEX
    Explanations

    vb

    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
     patente
    -0.09
     válida
    -0.09
    pickup
    -0.08
    Pickup
    -0.08
    中国特色社会主义
    -0.08
    pick
    -0.08
    azak
    -0.08
    MEA
    -0.08
     valide
    -0.07
    走
    -0.07
    POSITIVE LOGITS
     Grand
    0.08
     Dunn
    0.08
     Brou
    0.07
     gum
    0.07
     Gum
    0.07
     Jason
    0.07
     CRM
    0.07
    Gh
    0.07
    nat
    0.07
     Eld
    0.07
    Activations Density 0.001%

    No Known Activations