© 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. 23-RESID-POST-AA
    11. 49245
    Prev
    Next
    INDEX
    Explanations

    say soda

    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
     drinks
    -0.09
     Drinks
    -0.09
     beverages
    -0.08
     ontbij
    -0.08
     dr
    -0.08
     Dr
    -0.08
     sauce
    -0.08
    onado
    -0.08
    ouns
    -0.08
     Nación
    -0.08
    POSITIVE LOGITS
     sparkling
    0.15
     club
    0.15
     Club
    0.14
    Club
    0.14
     क्लब
    0.13
    club
    0.13
     hielo
    0.12
     mynta
    0.12
     mudd
    0.12
     carbonation
    0.12
    Activations Density 0.022%

    No Known Activations