© 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. 29024
    Prev
    Next
    INDEX
    Explanations

    基础

    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
     Verlust
    -0.09
     Denn
    -0.09
     Stair
    -0.09
     Vorstellungen
    -0.08
     기준
    -0.08
    欧
    -0.08
     Dav
    -0.08
     Anand
    -0.08
    Passwords
    -0.08
    ുവര
    -0.08
    POSITIVE LOGITS
    设施
    0.10
     amenities
    0.09
    設備
    0.08
     encontr
    0.08
     kindly
    0.08
     hus
    0.07
     semic
    0.07
     sé
    0.07
     despert
    0.07
     posed
    0.07
    Activations Density 0.003%

    No Known Activations