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. 54014
    Prev
    Next
    INDEX
    Explanations

    control

    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
     Cups
    -0.09
    豆
    -0.09
     TIFF
    -0.08
     Küchen
    -0.08
     cups
    -0.08
     Salz
    -0.08
    zingen
    -0.08
    essing
    -0.08
     cloves
    -0.08
     Grinding
    -0.08
    POSITIVE LOGITS
    bah
    0.08
    .Navigate
    0.08
     ila
    0.08
     commander
    0.08
     tuge
    0.08
     differential
    0.08
    Authorize
    0.08
     controllers
    0.08
     trajectories
    0.08
     жел
    0.08
    Activations Density 0.006%

    No Known Activations