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. 7-RESID-POST-AA
    6. 131060
    Prev
    Next
    INDEX
    Explanations

    climate change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dani
    -0.09
     CPM
    -0.08
     DAM
    -0.08
     tré
    -0.08
    tritt
    -0.07
    谜
    -0.07
     Nakam
    -0.07
     väl
    -0.07
     trick
    -0.07
     ol
    -0.07
    POSITIVE LOGITS
    0.09
    æng
    0.08
    -floating
    0.08
     Refrigerator
    0.07
     mornings
    0.07
    .gov
    0.07
    Lip
    0.07
     afternoons
    0.07
    shr
    0.07
    ha
    0.07
    Activations Density 0.000%

    No Known Activations