Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113047
    Prev
    Next
    INDEX
    Explanations

    statistical ratios and risks

    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
     baller
    -0.08
     what's
    -0.08
     drummer
    -0.07
    matter
    -0.07
    	memset
    -0.07
     ANSI
    -0.07
     तार
    -0.07
     those
    -0.07
     escrow
    -0.07
    兵
    -0.07
    POSITIVE LOGITS
     symptomatic
    0.10
     Epidemi
    0.08
     ratios
    0.08
     COPD
    0.08
     Lifestyle
    0.08
    病例
    0.08
    _ratio
    0.08
     epidemi
    0.08
     महामारी
    0.08
    疾病
    0.08
    Activations Density 0.009%

    No Known Activations