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. 11-RESID-POST-AA
    6. 102804
    Prev
    Next
    INDEX
    Explanations

    Pytorch code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     उज
    -0.08
    �்கள்
    -0.08
    illian
    -0.08
     جذ
    -0.08
     imprison
    -0.08
     edu
    -0.08
     triana
    -0.08
     bachelor
    -0.08
    pedia
    -0.07
     श्री
    -0.07
    POSITIVE LOGITS
    Comput
    0.08
     probing
    0.08
     computational
    0.08
     traversal
    0.08
    durch
    0.08
    ocr
    0.08
    Traversal
    0.08
     కార్య
    0.08
    Durch
    0.07
    .cpu
    0.07
    Activations Density 0.001%

    No Known Activations