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. 58378
    Prev
    Next
    INDEX
    Explanations

    帮助

    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
     handi
    -0.09
     bastante
    -0.08
     ce
    -0.08
    ball
    -0.08
     والے
    -0.07
     والی
    -0.07
     بشأن
    -0.07
    rok
    -0.07
    bereich
    -0.07
     Ball
    -0.07
    POSITIVE LOGITS
    理解
    0.08
     समझ
    0.08
    ,实现
    0.08
     pinpoint
    0.08
    (es
    0.08
     fears
    0.08
    0.08
    找到
    0.07
     अपन
    0.07
     сор
    0.07
    Activations Density 0.005%

    No Known Activations