© 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. 19583
    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
    جلة
    -0.10
    _common
    -0.08
     juba
    -0.08
    лә
    -0.08
    فت
    -0.08
    Common
    -0.08
    ساس
    -0.08
    اليب
    -0.08
    住所
    -0.07
    _gap
    -0.07
    POSITIVE LOGITS
     mehreren
    0.09
     meerdere
    0.09
     หรือ
    0.08
     ulti
    0.08
     Receiving
    0.08
     двух
    0.08
    illende
    0.08
     múltiples
    0.08
    ırı
    0.08
     někol
    0.08
    Activations Density 0.080%

    No Known Activations