Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19756
    Prev
    Next
    INDEX
    Explanations

    mathematical functions

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     والف
    -0.10
    ється
    -0.09
    етров
    -0.09
     شدند
    -0.09
     هستند
    -0.09
     енг
    -0.09
    ುತ್ತಿದೆ
    -0.09
    ються
    -0.09
     evenings
    -0.09
    .»↵↵
    -0.08
    POSITIVE LOGITS
     asked
    0.08
     ask
    0.07
     want
    0.07
    5
    0.07
    ,谢谢
    0.07
    数
    0.07
    最终
    0.07
     answer
    0.07
    9
    0.07
     how
    0.06
    Activations Density 0.040%

    No Known Activations