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. 23-RESID-POST-AA
    6. 97969
    Prev
    Next
    INDEX
    Explanations

    الب

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (B
    -0.07
    VES
    -0.07
    VE
    -0.07
    AE
    -0.07
    蓝
    -0.07
     contr
    -0.07
    พัน
    -0.07
     Veg
    -0.07
    Contr
    -0.07
    're
    -0.07
    POSITIVE LOGITS
     اسان
    0.08
     analyzes
    0.08
     فایل
    0.08
     وصل
    0.08
     קל
    0.08
    agés
    0.08
    adir
    0.08
     teško
    0.08
     ș
    0.08
     טר
    0.08
    Activations Density 0.001%

    No Known Activations