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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 106307
    Prev
    Next
    INDEX
    Explanations

    with

    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
     অন্যতম
    -0.10
     Ausland
    -0.08
     তাই
    -0.08
     salvo
    -0.08
    吨
    -0.08
     tonne
    -0.08
     taxed
    -0.08
     ולכן
    -0.08
     española
    -0.07
     Guaranteed
    -0.07
    POSITIVE LOGITS
     colleagues
    0.09
    0.08
     Eth
    0.08
     lush
    0.08
     surrounding
    0.08
     classmates
    0.08
    (Camera
    0.08
    رافق
    0.07
     greenery
    0.07
    راق
    0.07
    Activations Density 0.021%

    No Known Activations