© 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. 64609
    Prev
    Next
    INDEX
    Explanations

    Japan

    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
     manner
    -0.08
     odor
    -0.07
    حم
    -0.07
    孔
    -0.07
     debts
    -0.07
     ọgụ
    -0.07
     parap
    -0.07
    منت
    -0.07
    ूपी
    -0.07
    ạn
    -0.07
    POSITIVE LOGITS
     restraint
    0.08
     verso
    0.08
     Originally
    0.08
     дерево
    0.08
    mir
    0.07
     lobster
    0.07
    isphere
    0.07
    sed
    0.07
     illustrator
    0.07
     avi
    0.07
    Activations Density 0.011%

    No Known Activations