© 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. 19-RESID-POST-AA
    11. 18780
    Prev
    Next
    INDEX
    Explanations

    "used"

    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
     ngunit
    -0.10
     있지만
    -0.09
    yllä
    -0.09
     zarówno
    -0.09
     लेकिन
    -0.09
    multiple
    -0.09
    ：</
    -0.09
     nejen
    -0.09
     preferably
    -0.09
     tẹlẹ
    -0.09
    POSITIVE LOGITS
     used
    0.14
     Used
    0.11
     related
    0.10
     ginagamit
    0.10
    用于
    0.10
    "?
    0.10
     utilisés
    0.10
     digunakan
    0.10
    Used
    0.10
     används
    0.10
    Activations Density 0.089%

    No Known Activations