© 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. 45475
    Prev
    Next
    INDEX
    Explanations

    述

    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
     meals
    -0.08
     Meals
    -0.08
    monster
    -0.08
     Monster
    -0.07
     brak
    -0.07
     Monk
    -0.07
     Genius
    -0.07
     monsters
    -0.07
     Grimm
    -0.07
     monster
    -0.07
    POSITIVE LOGITS
     pertinent
    0.09
    些什么
    0.09
    ัติ
    0.09
    אלה
    0.08
     там
    0.08
     ngendlela
    0.08
    าด
    0.08
     pamusoro
    0.08
     topics
    0.08
    Supported
    0.08
    Activations Density 0.002%

    No Known Activations