© 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. 23-RESID-POST-AA
    11. 50238
    Prev
    Next
    INDEX
    Explanations

    Ind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Leer
    -0.09
     Ry
    -0.08
    ayam
    -0.08
     IIT
    -0.08
     qe
    -0.08
    leer
    -0.08
     dejav
    -0.08
     passar
    -0.08
     Leer
    -0.07
     qəbul
    -0.07
    POSITIVE LOGITS
    igenous
    0.15
    ígen
    0.12
    igen
    0.11
    spire
    0.10
     Indigenous
    0.09
     indigenous
    0.09
    ians
    0.08
     indígen
    0.08
     indígenas
    0.08
    @end
    0.08
    Activations Density 0.001%

    No Known Activations