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. 53838
    Prev
    Next
    INDEX
    Explanations

    persistence

    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
    0
    -0.07
    ㅇ
    -0.07
     strony
    -0.07
     stands
    -0.07
    사항
    -0.07
     Irvine
    -0.07
     tail
    -0.07
     constants
    -0.07
     meaningful
    -0.07
    >>↵↵
    -0.07
    POSITIVE LOGITS
    ห่ง
    0.10
    (mapped
    0.09
     cunning
    0.09
     cripple
    0.08
     қамтамасыз
    0.08
     প্রতিষ্ঠ
    0.08
     summoned
    0.08
     heureuse
    0.08
     орнал
    0.08
     ปี
    0.08
    Activations Density 0.001%

    No Known Activations