© 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. 21776
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     some
    -0.12
     关于
    -0.10
     někter
    -0.10
     给
    -0.10
     この
    -0.10
     或
    -0.10
     就
    -0.10
     sommige
    -0.10
     此
    -0.09
     哪
    -0.09
    POSITIVE LOGITS
    عديد
    0.22
    ولايات
    0.19
    مرأة
    0.19
    مواد
    0.19
    كسارة
    0.18
    نساء
    0.18
    طرق
    0.18
    ارتفاع
    0.17
    زيادة
    0.17
    بحث
    0.17
    Activations Density 0.008%

    No Known Activations