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. 29874
    Prev
    Next
    INDEX
    Explanations

    standardized

    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
     ésta
    -0.09
     weave
    -0.08
     weaving
    -0.08
    	local
    -0.08
    	l
    -0.08
    -0.08
     éste
    -0.07
    unordered
    -0.07
    plan
    -0.07
    	from
    -0.07
    POSITIVE LOGITS
     государственных
    0.13
     ceremonies
    0.09
     informes
    0.09
     государственного
    0.09
     रिपोर्ट
    0.08
     reporters
    0.08
     платформ
    0.08
     inflated
    0.08
     отчет
    0.08
    بس
    0.08
    Activations Density 0.004%

    No Known Activations