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. 130980
    Prev
    Next
    INDEX
    Explanations

    energy

    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
     icy
    -0.08
     memilih
    -0.08
     improving
    -0.08
     Improving
    -0.08
     ترقي
    -0.07
     accumulating
    -0.07
     advancing
    -0.07
     benefiting
    -0.07
     �
    -0.07
     Installing
    -0.07
    POSITIVE LOGITS
     consumption
    0.21
     usage
    0.21
     requirement
    0.19
     draw
    0.18
     expenditure
    0.18
     expenditures
    0.17
     requirements
    0.17
    需求
    0.17
    verbrauch
    0.17
     demand
    0.17
    Activations Density 0.049%

    No Known Activations