© 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. 24950
    Prev
    Next
    INDEX
    Explanations

    Beverages and drinking

    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
    riors
    -0.10
    	Copyright
    -0.09
     IRQ
    -0.09
    rechts
    -0.09
    bbs
    -0.09
    igslist
    -0.09
    aints
    -0.09
     Constraint
    -0.08
     archaeological
    -0.08
    _XML
    -0.08
    POSITIVE LOGITS
     напит
    0.19
     beverage
    0.19
     beverages
    0.17
     drinks
    0.15
    饮
    0.14
     bebidas
    0.14
     bebida
    0.14
     cocktails
    0.14
     boissons
    0.14
     Getränke
    0.13
    Activations Density 0.110%

    No Known Activations