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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 63850
    Prev
    Next
    INDEX
    Explanations

    We

    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
     situé
    -0.08
     nbr
    -0.07
     ఉంటుంది
    -0.07
     referido
    -0.07
    Them
    -0.07
     conflicto
    -0.07
    opri
    -0.07
    Kath
    -0.07
     Farn
    -0.07
    zó
    -0.07
    POSITIVE LOGITS
     guys
    0.08
     zaten
    0.08
     lasers
    0.08
     উচিত
    0.08
     insan
    0.08
     GNU
    0.08
     wake
    0.08
    eders
    0.07
    	M
    0.07
    	return
    0.07
    Activations Density 0.018%

    No Known Activations