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. 53912
    Prev
    Next
    INDEX
    Explanations

    product

    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
     southeastern
    -0.09
    /sidebar
    -0.09
    olone
    -0.08
    imid
    -0.08
     Mendoza
    -0.08
    aksi
    -0.08
    STONE
    -0.08
    ablement
    -0.08
     nostalgic
    -0.08
    لمان
    -0.08
    POSITIVE LOGITS
    就是
    0.08
     dará
    0.07
     dê
    0.07
     dando
    0.07
     misconduct
    0.07
     carcin
    0.07
     ऋ
    0.07
    0.07
    摄
    0.07
     घेत
    0.07
    Activations Density 0.016%

    No Known Activations