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. 120257
    Prev
    Next
    INDEX
    Explanations

    seed

    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
     Metric
    -0.08
    Multiplier
    -0.08
    Metric
    -0.08
     Peak
    -0.07
     Ene
    -0.07
    ಳಿ
    -0.07
    !!
    -0.07
    Post
    -0.07
     Metallic
    -0.07
     multiplier
    -0.07
    POSITIVE LOGITS
     பள்ள
    0.08
     sekolah
    0.08
     classroom
    0.08
     intoler
    0.07
     écoles
    0.07
    자리
    0.07
     oldukça
    0.07
     বিদ্যাল
    0.07
     અ
    0.07
     خانه
    0.07
    Activations Density 0.001%

    No Known Activations