Model techniques map
Techniquesmodel architecturechannel mixermixture of expertsexpert routing

specific method · filed under model architecture

Top-k expert routing with softmax over selected experts

Selects the top-k experts per token and weights their outputs using softmax over only the selected experts.

source
1
model
1
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

For both models, we select the top- experts for each token given by the router, and weight the output of each expert by the softmax of the router projection over only the selected experts.

coremodel architecturein gpt-oss-120b and gpt-oss-20bOpenAI

Filed alongside

Other methods under model architecture :: channel mixer :: mixture of experts :: expert routing.