© 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. 19-RESID-POST-AA
    11. 102537
    Prev
    Next
    INDEX
    Explanations

    "patch"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    াংল
    -0.09
    न्त्र
    -0.08
     okus
    -0.08
     consequat
    -0.08
     आकर्ष
    -0.08
     طن
    -0.08
    ्कार
    -0.07
     Outcomes
    -0.07
    大乐透
    -0.07
    lcool
    -0.07
    POSITIVE LOGITS
     patches
    0.32
     patch
    0.31
    Patch
    0.29
    patch
    0.28
     Patch
    0.28
    _patch
    0.28
     patched
    0.28
    .patch
    0.27
     PATCH
    0.25
    _PATCH
    0.24
    Activations Density 0.030%

    No Known Activations