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. 65895
    Prev
    Next
    INDEX
    Explanations

    Testing/Tests

    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
    枝
    -0.08
    ueil
    -0.08
    ika
    -0.08
     Eh
    -0.07
    /UI
    -0.07
     exaggerated
    -0.07
    'S
    -0.07
    /navigation
    -0.07
     provenientes
    -0.07
     Aa
    -0.07
    POSITIVE LOGITS
    报名
    0.10
     псих
    0.10
     aanvragen
    0.09
     برگزار
    0.09
     Durchführung
    0.09
     신청
    0.09
    中心官网
    0.09
     schedule
    0.09
     psych
    0.09
     অনুষ্ঠিত
    0.09
    Activations Density 0.022%

    No Known Activations