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. 18987
    Prev
    Next
    INDEX
    Explanations

    math terms

    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
     കഴ
    -0.09
     campaigns
    -0.08
     brig
    -0.08
    Prepar
    -0.08
     Prepar
    -0.08
     prepar
    -0.08
     منص
    -0.08
    軽
    -0.08
     lond
    -0.08
     Riverside
    -0.08
    POSITIVE LOGITS
    数学
    0.13
     математ
    0.13
     गण
    0.12
     fibonacci
    0.12
     mathematical
    0.12
     mathem
    0.12
     mathematics
    0.12
     matem
    0.11
     Mathematical
    0.11
     вычис
    0.11
    Activations Density 0.149%

    No Known Activations