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. 55982
    Prev
    Next
    INDEX
    Explanations

    -content

    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
     Preisen
    -0.08
     Dirty
    -0.08
    .Enums
    -0.07
     Stable
    -0.07
     epistem
    -0.07
    Restrictions
    -0.07
     ep
    -0.07
    .et
    -0.07
     epidemic
    -0.07
    ánek
    -0.07
    POSITIVE LOGITS
    .&
    0.08
     rainbow
    0.08
    :center
    0.08
     ಹರ
    0.07
     marina
    0.07
     Gucci
    0.07
     eyeb
    0.07
    /end
    0.07
     geograf
    0.07
     pancake
    0.07
    Activations Density 0.001%

    No Known Activations