© 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. 70794
    Prev
    Next
    INDEX
    Explanations

    YouTube links

    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
    的话
    -0.08
     할
    -0.08
    Designation
    -0.08
     designation
    -0.07
     সম্প্র
    -0.07
     calcul
    -0.07
    Рас
    -0.07
     Curse
    -0.07
     hérit
    -0.07
    ペ
    -0.07
    POSITIVE LOGITS
     SPDX
    0.08
    ોના
    0.08
    42
    0.08
    ують
    0.08
     instanceof
    0.08
    ોઈ
    0.08
    58
    0.08
    <typename
    0.08
    _so
    0.08
    auche
    0.08
    Activations Density 0.001%

    No Known Activations