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. 43279
    Prev
    Next
    INDEX
    Explanations

    computer science/math text

    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
     பண
    -0.09
     வேலை
    -0.08
    新的
    -0.08
    ۶
    -0.08
     tjetër
    -0.08
     kontr
    -0.07
     புதிய
    -0.07
     desider
    -0.07
    seven
    -0.07
     morgen
    -0.07
    POSITIVE LOGITS
     birbir
    0.13
     서로
    0.11
     miteinander
    0.10
     independientes
    0.09
     одинаков
    0.09
     أنفس
    0.09
     కలిసి
    0.09
     nhau
    0.09
     gegense
    0.09
    Together
    0.09
    Activations Density 0.097%

    No Known Activations