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. 26908
    Prev
    Next
    INDEX
    Explanations

    first

    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
     intertw
    -0.08
    ų
    -0.08
    imuth
    -0.07
     purported
    -0.07
    уун
    -0.07
     fundamentally
    -0.07
    pi
    -0.07
    profiles
    -0.07
    პრ
    -0.07
    ဝ
    -0.07
    POSITIVE LOGITS
    第一次
    0.10
     lần
    0.10
     опы
    0.09
     माम
    0.09
    首次
    0.09
    逐
    0.08
     ausprob
    0.08
    日在
    0.08
    ервые
    0.08
     oefenen
    0.08
    Activations Density 0.044%

    No Known Activations