Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 55964
    Prev
    Next
    INDEX
    Explanations

    carbon removal

    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
    作品
    -0.08
     scherpe
    -0.08
     작품
    -0.08
     previews
    -0.08
     Kaj
    -0.07
     ती
    -0.07
     mero
    -0.07
     presentations
    -0.07
    教授
    -0.07
    /tutorial
    -0.07
    POSITIVE LOGITS
     seques
    0.12
    soil
    0.10
     dioxide
    0.10
     greenhouse
    0.10
     sunlight
    0.09
     soils
    0.09
     océ
    0.09
     mitigation
    0.09
     soil
    0.09
     atta
    0.09
    Activations Density 0.013%

    No Known Activations