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. 98630
    Prev
    Next
    INDEX
    Explanations

    ت

    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
    िष्ट
    -0.07
    ्यूटर
    -0.07
     she
    -0.07
    िंक
    -0.07
    ించాలని
    -0.07
     he
    -0.07
     herk
    -0.07
    rein
    -0.07
     roaming
    -0.07
    شة
    -0.07
    POSITIVE LOGITS
    وده
    0.12
    وافق
    0.10
    ظاهر
    0.10
    په
    0.10
    جهیز
    0.10
    ندی
    0.10
    لفات
    0.09
    بادل
    0.09
    کر
    0.09
    كيف
    0.09
    Activations Density 0.001%

    No Known Activations