© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 49421
    Prev
    Next
    INDEX
    Explanations

    Arabic texts

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uje
    -0.08
    ucun
    -0.07
     typeof
    -0.07
    ujejo
    -0.07
    ’s
    -0.07
     iedereen
    -0.07
    ़
    -0.07
    ectl
    -0.07
    ened
    -0.07
     yra
    -0.07
    POSITIVE LOGITS
    بداع
    0.15
    قامة
    0.15
    ظهر
    0.15
    ظهار
    0.15
    حياء
    0.13
    دارة
    0.13
    سرائيل
    0.13
    ب
    0.13
    حدث
    0.13
    حدى
    0.13
    Activations Density 0.003%

    No Known Activations