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. 76415
    Prev
    Next
    INDEX
    Explanations

    punctuation and connector words

    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
    արմ
    -0.08
    մ
    -0.08
     Slovenije
    -0.08
     που
    -0.08
     podnik
    -0.08
    avlj
    -0.07
     ایم
    -0.07
     Ced
    -0.07
    مند
    -0.07
    …but
    -0.07
    POSITIVE LOGITS
    .He
    0.08
    illus
    0.07
     бары
    0.07
     recently
    0.07
    OUNT
    0.07
     BAT
    0.07
     Kuchen
    0.07
     tablas
    0.07
    ograms
    0.07
     illusion
    0.07
    Activations Density 0.128%

    No Known Activations