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. 18811
    Prev
    Next
    INDEX
    Explanations

    =

    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
     mengenai
    -0.08
    ={↵
    -0.08
     Doyle
    -0.08
     Lad
    -0.08
     Tram
    -0.07
    ]:↵↵
    -0.07
     Thompson
    -0.07
    _coordinate
    -0.07
    ଗ
    -0.07
    ":↵↵
    -0.07
    POSITIVE LOGITS
     아니
    0.09
     bureau
    0.08
     '';↵
    0.08
     مسائل
    0.08
     اسے
    0.08
     aangeven
    0.08
     әрі
    0.08
    ൂര
    0.08
     മറ്റ്
    0.08
    \",\"
    0.08
    Activations Density 0.008%

    No Known Activations