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. 106280
    Prev
    Next
    INDEX
    Explanations

    citing research

    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
    (_('
    -0.09
    _->
    -0.08
    (+
    -0.08
    cura
    -0.08
     독
    -0.08
     넘
    -0.08
    (_("
    -0.08
    itorinaa
    -0.08
    (ord
    -0.08
     глад
    -0.08
    POSITIVE LOGITS
     Many
    0.09
     available
    0.08
    Available
    0.08
     Websites
    0.08
     online
    0.08
     known
    0.08
     many
    0.08
    -known
    0.08
    Many
    0.08
     existing
    0.08
    Activations Density 0.029%

    No Known Activations