© 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. 31407
    Prev
    Next
    INDEX
    Explanations

    Fragmented text snippets

    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
     Tele
    -0.08
    为空
    -0.08
    吹
    -0.08
    zne
    -0.08
     ವೇಳೆ
    -0.08
     ak
    -0.08
     viene
    -0.08
    decl
    -0.07
     দিতে
    -0.07
     wsk
    -0.07
    POSITIVE LOGITS
     Jr
    0.08
    shire
    0.08
     County
    0.08
    さん
    0.08
    先生
    0.08
     Joel
    0.08
     II
    0.08
    sburg
    0.08
     thrive
    0.08
    IV
    0.08
    Activations Density 0.338%

    No Known Activations