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. 11-RESID-POST-AA
    6. 9189
    Prev
    Next
    INDEX
    Explanations

    mathematical reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    予定
    -0.08
     예정
    -0.08
     Bartlett
    -0.08
     Yosemite
    -0.08
     soreness
    -0.08
     plán
    -0.08
     Rum
    -0.08
     Pong
    -0.08
    .rhino
    -0.08
     beck
    -0.08
    POSITIVE LOGITS
     digits
    0.17
    Digits
    0.16
    digits
    0.15
    _digits
    0.15
    -digit
    0.13
    Digit
    0.12
     decimal
    0.11
     циф
    0.11
     dí
    0.10
    (decimal
    0.10
    Activations Density 0.068%

    No Known Activations