I have heard that uncensorted gpt-oss is not very good because of it being trained mainly on synthetic data. Is not not true?

Iirc abliteration (ablation?) can be done without "training" and is pretty quick. It finds the individual weights related to the concept you want to ablate, and modifies those weights to "deactivate" them. Precision brain surgery, to anthropomorphize.

The problem with synthetic data would be that the censored information would not be in the training data at all.

Very interesting! Do the benchmarks hold up well or does it reduce performance in other areas too?