Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 18906
    Prev
    Next
    INDEX
    Explanations

    say "each"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    volving
    -0.08
    .
    -0.07
    ୍
    -0.07
     quelques
    -0.07
    ୀ
    -0.07
     partir
    -0.07
    ା
    -0.06
    -0.06
    作为
    -0.06
    -inclusive
    -0.06
    POSITIVE LOGITS
     प्रत्येक
    0.38
     ഓരോ
    0.37
     Each
    0.37
    Each
    0.37
     each
    0.37
    每
    0.36
     દરેક
    0.36
    ,每
    0.36
     ప్రతి
    0.35
     fiecare
    0.34
    Activations Density 0.148%

    No Known Activations