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. 12903
    Prev
    Next
    INDEX
    Explanations

    arrangements order sequences

    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
     فی
    -0.08
    なが
    -0.08
     نور
    -0.07
    bereiche
    -0.07
    Https
    -0.07
     bleeding
    -0.07
     ış
    -0.07
     اړ
    -0.07
     bih
    -0.07
     Maur
    -0.07
    POSITIVE LOGITS
    排列
    0.10
     Arrangement
    0.10
     Reihen
    0.10
     arrangement
    0.09
     Sequence
    0.08
    _SEQUENCE
    0.08
     sequ
    0.08
     Sequ
    0.08
     sequences
    0.08
     configs
    0.08
    Activations Density 0.034%

    No Known Activations