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. 43746
    Prev
    Next
    INDEX
    Explanations

    2

    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
     freshly
    -0.08
     Century
    -0.08
    (Store
    -0.08
     век
    -0.08
     Raising
    -0.07
    (ll
    -0.07
     Raise
    -0.07
     Updating
    -0.07
     Inspiration
    -0.07
     Inspirations
    -0.07
    POSITIVE LOGITS
    بعاد
    0.08
     object's
    0.08
     rôle
    0.08
     teles
    0.08
    cura
    0.08
     paš
    0.07
    كَ
    0.07
     FIFA
    0.07
    TEGR
    0.07
     قد
    0.07
    Activations Density 0.039%

    No Known Activations