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. 30624
    Prev
    Next
    INDEX
    Explanations

    exposed

    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
     보내
    -0.08
     বিন
    -0.08
     MIME
    -0.08
     компании
    -0.07
     મોક
    -0.07
     negócio
    -0.07
     сәй
    -0.07
     Botan
    -0.07
     nausea
    -0.07
    -এর
    -0.07
    POSITIVE LOGITS
     Hardwood
    0.08
     traduction
    0.08
     dostup
    0.08
     vše
    0.08
     sulfate
    0.08
     craftsmen
    0.07
     grammatical
    0.07
     tabla
    0.07
    行政
    0.07
    presentation
    0.07
    Activations Density 0.001%

    No Known Activations