© 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. 108457
    Prev
    Next
    INDEX
    Explanations

    magic and fantasy

    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
     ameri
    -0.09
     Cristiano
    -0.09
    車
    -0.09
    Toyota
    -0.09
     samoch
    -0.08
     Toyota
    -0.08
    辆
    -0.08
     कोविड
    -0.08
     weekends
    -0.08
     รถ
    -0.08
    POSITIVE LOGITS
     मंत्र
    0.15
     Potion
    0.13
     potion
    0.13
     алх
    0.13
     മന്ത്ര
    0.12
    Potion
    0.12
     magical
    0.12
    Enchant
    0.12
     apprentice
    0.11
     enchant
    0.11
    Activations Density 0.044%

    No Known Activations