© 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. 31245
    Prev
    Next
    INDEX
    Explanations

    shepherd/pastor/psalms

    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
     streak
    -0.08
    eroon
    -0.08
    andie
    -0.08
     Macy
    -0.08
    iş
    -0.07
     fires
    -0.07
    IVATE
    -0.07
    lane
    -0.07
    ongan
    -0.07
     Confederate
    -0.07
    POSITIVE LOGITS
     allocator
    0.09
    公众
    0.09
    Published
    0.09
    Publisher
    0.09
    سباب
    0.08
     Produktions
    0.08
    生产
    0.08
    _allocator
    0.08
     الإنتاج
    0.08
    出版社
    0.08
    Activations Density 0.001%

    No Known Activations