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. 54008
    Prev
    Next
    INDEX
    Explanations

    T

    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
     Ibn
    -0.09
     الله
    -0.08
     celestial
    -0.08
     judicial
    -0.08
     jurid
    -0.07
    ь
    -0.07
    -0.07
    538
    -0.07
     obedience
    -0.07
    형
    -0.07
    POSITIVE LOGITS
     Wiener
    0.08
     செல
    0.08
     صغيرة
    0.08
     stres
    0.08
     المالية
    0.08
     podat
    0.08
     LDL
    0.08
     sagt
    0.08
     ചെ
    0.08
     liten
    0.08
    Activations Density 0.004%

    No Known Activations