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. 15-RESID-POST-AA
    6. 19022
    Prev
    Next
    INDEX
    Explanations

    code syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     клі
    -0.08
    =-=-
    -0.07
    :A
    -0.07
    :B
    -0.07
    commended
    -0.07
    الات
    -0.07
     Boulder
    -0.07
     attracting
    -0.07
     Upcoming
    -0.07
     المنت
    -0.07
    POSITIVE LOGITS
     ಬಳಿಕ
    0.09
     ત્યાર
    0.09
     입력
    0.09
     سپس
    0.09
     ನಂತರ
    0.09
     අන
    0.09
     sonra
    0.08
     waarna
    0.08
     त्यस
    0.08
     थो
    0.08
    Activations Density 0.013%

    No Known Activations