© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111105
    Prev
    Next
    INDEX
    Explanations

    dimensional analysis and units

    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
    _MPI
    -0.07
     initials
    -0.07
    Announcement
    -0.07
    �
    -0.07
    elag
    -0.07
    üni
    -0.07
    .Serializable
    -0.07
    otry
    -0.07
     orderly
    -0.07
    ield
    -0.07
    POSITIVE LOGITS
     convertir
    0.14
     converting
    0.13
    _conversion
    0.13
    _converter
    0.13
     conversion
    0.12
     Conversion
    0.12
    Conversion
    0.12
     преобраз
    0.12
    conversion
    0.12
    转换
    0.11
    Activations Density 0.031%

    No Known Activations