© 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. 15-RESID-POST-AA
    11. 16291
    Prev
    Next
    INDEX
    Explanations

    c

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embark
    -0.08
     embarking
    -0.08
     الخدمات
    -0.08
     dorm
    -0.07
    Modern
    -0.07
    abetes
    -0.07
     خدمات
    -0.07
     ||
↵
    -0.07
    .thrift
    -0.07
     facilities
    -0.07
    POSITIVE LOGITS
    。この
    0.10
     அன்று
    0.09
     הזו
    0.09
    という
    0.09
     және
    0.09
    とな
    0.09
     oraz
    0.09
     மற்றும்
    0.08
    (note
    0.08
    ---
    0.08
    Activations Density 0.181%

    No Known Activations