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. 54001
    Prev
    Next
    INDEX
    Explanations

    lasso regression

    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
    וש
    -0.08
     direitos
    -0.07
    �
    -0.07
     inúmer
    -0.07
     questões
    -0.07
    atra
    -0.07
     dump
    -0.07
     horror
    -0.07
     כבר
    -0.07
    ושה
    -0.07
    POSITIVE LOGITS
     auto
    0.08
    -cols
    0.08
    -adjust
    0.08
    asti
    0.08
    jandro
    0.07
    utils
    0.07
    -analysis
    0.07
     Brothers
    0.07
    -validation
    0.07
    Sous
    0.07
    Activations Density 0.001%

    No Known Activations