© 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. 44649
    Prev
    Next
    INDEX
    Explanations

    cmake commands

    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
    精选
    -0.10
     astrology
    -0.10
     dazzling
    -0.10
     horoscope
    -0.10
     दिव
    -0.09
     Wealth
    -0.09
     соверш
    -0.09
     gambler
    -0.09
     السما
    -0.09
     pensamientos
    -0.09
    POSITIVE LOGITS
     Qt
    0.12
     vtk
    0.11
    Qt
    0.11
    vtk
    0.10
     clang
    0.10
     configure
    0.10
     Debian
    0.09
    _cpp
    0.09
    _INSTALL
    0.09
     itk
    0.09
    Activations Density 0.012%

    No Known Activations