© 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. 110363
    Prev
    Next
    INDEX
    Explanations

    Commas and words ending in "ing"

    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
     accented
    -0.10
     vom
    -0.08
    ATFORM
    -0.08
    YPTO
    -0.08
     Alas
    -0.08
    वर्क
    -0.08
     AT
    -0.07
    _PROVIDER
    -0.07
    provider
    -0.07
     supplemented
    -0.07
    POSITIVE LOGITS
    诚
    0.08
    ্ধ
    0.08
     diálogo
    0.08
    沈
    0.07
     mij
    0.07
    困
    0.07
     subsidy
    0.07
     чест
    0.07
    icia
    0.07
    待遇
    0.07
    Activations Density 0.000%

    No Known Activations