© 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. 50112
    Prev
    Next
    INDEX
    Explanations

    say "his or he"

    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
     देती
    -0.15
     करती
    -0.15
     کرتی
    -0.14
     juntas
    -0.13
     करेगी
    -0.12
     सकती
    -0.11
     بها
    -0.11
     इनके
    -0.11
     استخدامها
    -0.10
     ती
    -0.10
    POSITIVE LOGITS
     his
    0.76
     그의
    0.64
    他的
    0.64
     he
    0.63
    ，他
    0.62
     he's
    0.61
     അദ്ദേഹ
    0.60
     അദ്ദേഹം
    0.59
    His
    0.59
     His
    0.59
    Activations Density 1.792%

    No Known Activations