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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 77267
    Prev
    Next
    INDEX
    Explanations

    How-to guides

    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
    微博
    -0.11
     marginalized
    -0.09
     Statistical
    -0.09
    -meta
    -0.09
     pedagog
    -0.08
    exual
    -0.08
     MOOCs
    -0.08
    榜
    -0.08
    .Mongo
    -0.08
     trajectories
    -0.08
    POSITIVE LOGITS
     DIY
    0.17
    施工
    0.16
     drywall
    0.16
    DIY
    0.16
     homeowners
    0.15
     homeowner
    0.14
    安装
    0.13
     installed
    0.13
     renovation
    0.13
     OSHA
    0.12
    Activations Density 0.030%

    No Known Activations