© 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. 5929
    Prev
    Next
    INDEX
    Explanations

    say the ending -ary

    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
     diagnosing
    -0.09
    welve
    -0.08
    uerzo
    -0.08
    診
    -0.08
     diagnosis
    -0.08
     buk
    -0.08
    uddle
    -0.08
    πού
    -0.08
     ಪು
    -0.08
    riangle
    -0.08
    POSITIVE LOGITS
    arial
    0.29
    aries
    0.22
    ary
    0.22
    ities
    0.19
    ariales
    0.18
    ARY
    0.14
    erial
    0.14
    ários
    0.14
    ário
    0.13
    arius
    0.13
    Activations Density 0.003%

    No Known Activations