© 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. 91740
    Prev
    Next
    INDEX
    Explanations

    Plant cultivars

    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
    Probability
    -0.09
    Correlation
    -0.09
    利益
    -0.08
    Coronavirus
    -0.08
     بع
    -0.08
    Exclusive
    -0.08
    支付
    -0.08
    Payment
    -0.08
     incentiv
    -0.08
    Agora
    -0.07
    POSITIVE LOGITS
     ornamental
    0.13
     woody
    0.11
     gardeners
    0.11
     декоратив
    0.10
     hortic
    0.10
     shrubs
    0.10
     hardy
    0.10
     foliage
    0.09
     Swing
    0.09
     garden
    0.09
    Activations Density 0.042%

    No Known Activations