© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 48653
    Prev
    Next
    INDEX
    Explanations

    被

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     omzet
    -0.09
     bagian
    -0.09
     біздің
    -0.09
     části
    -0.09
     श्रृ
    -0.08
    	of
    -0.08
     कांग्रेस
    -0.08
     Corporation
    -0.08
     Limestone
    -0.08
     часть
    -0.08
    POSITIVE LOGITS
    害
    0.10
     urge
    0.09
     told
    0.09
     tempted
    0.08
    -t
    0.08
     urged
    0.08
     tired
    0.08
    讨
    0.08
    -me
    0.08
    ness
    0.08
    Activations Density 0.041%

    No Known Activations