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. 97109
    Prev
    Next
    INDEX
    Explanations

    Geothermal activity

    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
     avión
    -0.09
     sailed
    -0.09
     Crop
    -0.09
    Crop
    -0.09
     pallets
    -0.09
     fragt
    -0.08
     cereal
    -0.08
     crop
    -0.08
     burglary
    -0.08
    収納
    -0.08
    POSITIVE LOGITS
     geothermal
    0.24
     Reykj
    0.20
     gey
    0.19
     fumar
    0.18
     thermal
    0.17
     springs
    0.17
     volcanic
    0.15
     steaming
    0.15
     steam
    0.15
     bubbling
    0.15
    Activations Density 0.012%

    No Known Activations