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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103230
    Prev
    Next
    INDEX
    Explanations

    diverse languages and punctuation

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -ċ
    -0.10
    -0.09
    	actual
    -0.09
    -ġ
    -0.09
    ŝ
    -0.09
    nię
    -0.09
     азамат
    -0.08
     practition
    -0.08
    	all
    -0.08
     сир
    -0.08
    POSITIVE LOGITS
     seu
    0.08
    ↵↵
    0.08
     suoi
    0.08
     sua
    0.08
     relevant
    0.08
     it
    0.07
     找
    0.07
     તેની
    0.07
    )}>
    0.07
    0.07
    Activations Density 0.020%
    No Known Activations