© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 45533
    Prev
    Next
    INDEX
    Explanations

    awards for good work

    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
     occasions
    -0.08
    漫
    -0.08
    ško
    -0.08
     slab
    -0.07
    _tex
    -0.07
     depreciation
    -0.07
     الثقيلة
    -0.07
    等级
    -0.07
     disclaim
    -0.07
     polygon
    -0.07
    POSITIVE LOGITS
     activism
    0.15
     NGOs
    0.13
     grassroots
    0.13
     initiatives
    0.13
     activists
    0.12
     nonprofits
    0.12
    Innov
    0.12
     philanthrop
    0.12
     activist
    0.12
     philanth
    0.12
    Activations Density 0.077%

    No Known Activations