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. 43309
    Prev
    Next
    INDEX
    Explanations

    SCP articles with numbers

    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
     objectives
    -0.08
    .footer
    -0.08
     müh
    -0.08
    去
    -0.08
    基层
    -0.07
    歉
    -0.07
    技巧
    -0.07
    �
    -0.07
    પૂર્ણ
    -0.07
     objectifs
    -0.07
    POSITIVE LOGITS
     discovered
    0.08
    Weapon
    0.08
     "!
    0.08
    "B
    0.08
     Persons
    0.08
    -haired
    0.08
     हथ
    0.08
     Weapon
    0.08
     havi
    0.08
     العن
    0.08
    Activations Density 0.004%

    No Known Activations