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. 54035
    Prev
    Next
    INDEX
    Explanations

    biblical texts

    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
    线程
    -0.09
     kı
    -0.09
    (UUID
    -0.08
     theoretical
    -0.08
     diab
    -0.08
     doctoral
    -0.08
     factorial
    -0.08
    erialized
    -0.08
    esign
    -0.08
    框
    -0.08
    POSITIVE LOGITS
     하나님
    0.09
     मंदिर
    0.09
     prostitutes
    0.08
     Syri
    0.08
    ו
    0.08
     마음
    0.08
     giants
    0.08
     worship
    0.08
     pagan
    0.07
     정말
    0.07
    Activations Density 0.025%

    No Known Activations