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. 98441
    Prev
    Next
    INDEX
    Explanations

    fire spread

    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
    FILTER
    -0.09
     FILTER
    -0.09
     Filter
    -0.09
    过滤
    -0.09
    Filter
    -0.09
    Filtering
    -0.09
    Fire
    -0.09
    _filter
    -0.08
    Firewall
    -0.08
    filter
    -0.08
    POSITIVE LOGITS
     acreage
    0.13
     spread
    0.13
     Spread
    0.12
    Spread
    0.12
     буш
    0.11
     spreads
    0.11
    spread
    0.11
     spreading
    0.11
    传播
    0.10
     behavior
    0.10
    Activations Density 0.015%

    No Known Activations