© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 102156
    Prev
    Next
    INDEX
    Explanations

    مل

    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
     หรือ
    -0.08
     เป็น
    -0.08
     jemand
    -0.07
     reasoning
    -0.07
    illiams
    -0.07
     Traditionally
    -0.07
     �
    -0.07
     Crisp
    -0.07
     или
    -0.07
    /loading
    -0.07
    POSITIVE LOGITS
    ائمة
    0.13
    حوق
    0.12
    ائم
    0.12
    تیا
    0.12
    ומען
    0.11
    جهه
    0.11
    حدة
    0.11
    ווים
    0.11
    מיד
    0.11
    ைய
    0.11
    Activations Density 0.002%

    No Known Activations