Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9061
    Prev
    Next
    INDEX
    Explanations

    trigonometry

    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
     %↵↵
    -0.10
     వెల్లడ
    -0.09
    _",
    -0.09
     deciso
    -0.08
     నేత
    -0.08
     alleges
    -0.08
     pesado
    -0.08
     насыщ
    -0.08
     ওঠ
    -0.08
    _brand
    -0.08
    POSITIVE LOGITS
     anywhere
    0.08
     daarvoor
    0.08
    有哪些
    0.08
     candidates
    0.07
    知ら
    0.07
    果
    0.07
    很多
    0.07
     intrins
    0.07
     Möglichkeiten
    0.07
    igu
    0.07
    Activations Density 0.096%

    No Known Activations