How to examine worst image regression losses?

I’ve been studying Fastai for a while, and am now using
it to participate in an image-related ML competition.

The task is regression, so I’m now trying to look at the
worst individual errors my model is making.
Is there a convenient way to do this in Fastai v1?
I would expect something similar to ClassificationInterpretation
(like RegressionInterpretation), but haven’t found an equivalent
for regression. Is there currently anything like that, or any
other convenient way to do it?