© 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. 111067
    Prev
    Next
    INDEX
    Explanations

    columnar data storage

    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
    稍
    -0.10
    略
    -0.08
    病毒
    -0.08
    确保
    -0.08
    192
    -0.08
     virus
    -0.08
    _hostname
    -0.08
     Coventry
    -0.08
    增加
    -0.08
     någon
    -0.08
    POSITIVE LOGITS
     SELECT
    0.10
     stored
    0.09
     조회
    0.09
     специализирован
    0.09
     faci
    0.08
     süt
    0.08
     opgeslagen
    0.08
    SELECT
    0.08
     মোক
    0.08
    fac
    0.08
    Activations Density 0.006%

    No Known Activations