© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97298
    Prev
    Next
    INDEX
    Explanations

    say "orn"

    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
     legislature
    -0.08
    工商
    -0.08
    Ví
    -0.08
     ради
    -0.08
     obesity
    -0.08
    .SIZE
    -0.08
    ख
    -0.08
    制
    -0.08
    卫生
    -0.08
    authority
    -0.07
    POSITIVE LOGITS
     weather
    0.10
    weather
    0.09
    be
    0.09
    mar
    0.08
    amiliar
    0.08
    ppa
    0.08
     Weather
    0.08
    -be
    0.08
    readcrumb
    0.08
     battle
    0.08
    Activations Density 0.001%

    No Known Activations