© 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. 99487
    Prev
    Next
    INDEX
    Explanations

    pepperoni pizza

    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
    midt
    -0.09
     hybr
    -0.08
    spartner
    -0.08
     Meth
    -0.08
     المغرب
    -0.07
     Thy
    -0.07
     Lucifer
    -0.07
     Libre
    -0.07
    тык
    -0.07
    Meth
    -0.07
    POSITIVE LOGITS
    Roster
    0.08
     roster
    0.08
    宴
    0.08
     UFO
    0.07
    来看
    0.07
     epidemi
    0.07
    erview
    0.07
    大片
    0.07
    iew
    0.07
     forensic
    0.07
    Activations Density 0.001%

    No Known Activations