© 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. 49943
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    日起
    -0.07
     invers
    -0.07
    achar
    -0.07
     Southern
    -0.07
    533
    -0.07
     Directory
    -0.07
    /job
    -0.07
     axle
    -0.07
     intimidated
    -0.07
    avigator
    -0.07
    POSITIVE LOGITS
    elitian
    0.08
    �
    0.08
    서
    0.08
    ortex
    0.08
     Suisse
    0.08
    (fin
    0.07
    mes
    0.07
     viện
    0.07
    (tr
    0.07
    οινων
    0.07
    Activations Density 0.000%

    No Known Activations