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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97993
    Prev
    Next
    INDEX
    Explanations

    midnight

    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
    егов
    -0.09
     Blockly
    -0.08
     besø
    -0.08
    bonjour
    -0.08
     declines
    -0.08
    $_['
    -0.08
    κεκρι
    -0.08
    Bonjour
    -0.08
    ṣe
    -0.08
    .Visit
    -0.08
    POSITIVE LOGITS
     午夜
    0.24
     midnight
    0.23
     Midnight
    0.21
    午夜
    0.20
     madrugada
    0.19
    凌晨
    0.18
     منتصف
    0.16
     ноч
    0.15
     gece
    0.15
     রাত
    0.15
    Activations Density 0.026%

    No Known Activations