© 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. 6030
    Prev
    Next
    INDEX
    Explanations

    Square roots and math

    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
     toss
    -0.08
     zet
    -0.08
    -0.07
     activo
    -0.07
    -ma
    -0.07
     FT
    -0.07
    MA
    -0.07
    ft
    -0.07
    ma
    -0.07
     griev
    -0.07
    POSITIVE LOGITS
     olymp
    0.09
    ځي
    0.08
    liers
    0.08
    ->___
    0.08
     ij
    0.08
     sebe
    0.08
    WORDS
    0.08
    ENSOR
    0.08
     Сан
    0.08
     scher
    0.08
    Activations Density 0.003%
    No Known Activations