© 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. 19176
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     cuáles
    -0.09
     كيف
    -0.08
     clos
    -0.08
     main
    -0.08
     cómo
    -0.07
     Central
    -0.07
    是多少钱
    -0.07
    mosis
    -0.07
    怎么看
    -0.07
     cuál
    -0.07
    POSITIVE LOGITS
    ും
    0.10
    ең
    0.09
    алеж
    0.09
    աբար
    0.09
    esseurs
    0.09
    देख
    0.09
    तः
    0.09
    ിടെ
    0.09
    ज्ञ
    0.09
    ്റെ
    0.09
    Activations Density 0.002%

    No Known Activations