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. 53033
    Prev
    Next
    INDEX
    Explanations

    is

    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
    స్తుతం
    -0.09
    ғни
    -0.08
    DRV
    -0.08
    Ae
    -0.08
    CO
    -0.08
     гэт
    -0.08
    doctoral
    -0.08
     Coil
    -0.08
     ինձ
    -0.07
    	assign
    -0.07
    POSITIVE LOGITS
     Tos
    0.07
     ওয়
    0.07
     लिंक
    0.07
    imaan
    0.07
    يلة
    0.06
     模
    0.06
    Maps
    0.06
     Händ
    0.06
     Sergio
    0.06
    ও
    0.06
    Activations Density 0.447%

    No Known Activations