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. 11-RESID-POST-AA
    6. 11931
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    acijos
    -0.07
     форма
    -0.07
    �
    -0.07
    иру
    -0.07
    изации
    -0.07
     ক্ষেত্রে
    -0.07
     biolog
    -0.07
    ্যম
    -0.07
    variant
    -0.07
    aceut
    -0.07
    POSITIVE LOGITS
    дать
    0.08
     перейти
    0.08
     spæ
    0.07
     Kol
    0.07
     reflector
    0.07
     Kon
    0.07
    DE
    0.07
     Mathieu
    0.07
     Gamma
    0.07
    tona
    0.07
    Activations Density 0.005%

    No Known Activations