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. 12723
    Prev
    Next
    INDEX
    Explanations

    体现

    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
     оған
    -0.09
     uburyo
    -0.08
     ity
    -0.08
     intervient
    -0.08
     reconnu
    -0.08
     оның
    -0.08
    klass
    -0.08
     Attractions
    -0.08
     бірнеше
    -0.08
     Tsy
    -0.08
    POSITIVE LOGITS
     будто
    0.08
    透露
    0.08
    姓名
    0.07
    呈
    0.07
     prescribing
    0.07
    北京时间
    0.07
     GPT
    0.07
    ેખ
    0.07
    ેન
    0.07
    即可
    0.07
    Activations Density 0.001%

    No Known Activations