© 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. 7499
    Prev
    Next
    INDEX
    Explanations

    disabilities support services

    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
     Being
    -0.08
     Woods
    -0.08
     Recorder
    -0.08
    bined
    -0.08
     Reads
    -0.08
    .smtp
    -0.07
     Archiv
    -0.07
     sages
    -0.07
     będą
    -0.07
    Being
    -0.07
    POSITIVE LOGITS
    '));↵↵
    0.08
    frastructure
    0.08
    抱
    0.08
    案例
    0.07
     insists
    0.07
     contempor
    0.07
    etails
    0.07
     inclusion
    0.07
     istr
    0.07
     недвижимости
    0.07
    Activations Density 0.025%

    No Known Activations