Neuroscientific studies often involve some form of group analysis over multiple participants. This requires alignment of recordings across participants. A naive solution is to assume that participants’ recordings can be aligned anatomically in sensor space. However, this assumption is likely violated due to anatomical and functional differences between individual brains. In magnetoencephalography (MEG) recordings the problem of inter-individual alignment is exacerbated by the susceptibility of MEG to individual cortical folding patterns as well as the inter-individual variability of sensor locations over the brain. Hence, an approach to combine MEG data over individual brains should relax the assumptions that brain anatomy and function are tightly linked and that the same sensors can capture functionally comparable brain activation across individuals. Here we use multiset canonical correlation analysis (M-CCA) to find a common representation of MEG activations recorded from different participants performing a similar task. Our approach applies M-CCA to transform data of multiple participants into a common space with maximum pairwise correlation between participants. Importantly, we derive a method to transform data from a new, previously unseen participant into this common representation. We demonstrate the superiority of the approach over simpler, previously used ones. To this end, we train single-trial inter-individual decoders on the common data representation from one set of participants and test the transfer of the models to data from a new participant who was neither included in finding the common space nor in the training of the decoder. Finally, we show that our approach requires only a small number of labeled data from the new participant. Our work demonstrates that inter-individual alignment via M-CCA has the potential for combining data of different participants and could become helpful in future endeavors on large open datasets. It also has potential applications in reducing training time of online brain-computer interfaces.