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. 384
    Prev
    Next
    INDEX
    Explanations

    Cyberpunk prompts in other language

    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
     wsp
    -0.08
    	↵	↵
    -0.08
     hukum
    -0.08
    510
    -0.08
     Закон
    -0.08
     RULE
    -0.07
     Verantwortung
    -0.07
    _RULE
    -0.07
     bow
    -0.07
    --------------------------------------------------------------------------↵
    -0.07
    POSITIVE LOGITS
    体现
    0.09
    整体
    0.09
    表现
    0.08
    ,并
    0.08
    别
    0.08
    度
    0.08
    ,有
    0.08
     mysl
    0.08
     Asturias
    0.08
    有
    0.07
    Activations Density 0.021%

    No Known Activations