This work explores the extension of channel charting, a technique for constructing low-dimensional representations of channel state information (CSI) through self-supervised learning, to wireless environments including reconfigurable intelligent surfaces (RIS). Channel charting has shown promise in pseudoposition based radio resource management applications by capturing spatial relationships between transmitters and receivers. We investigate the challenges and opportunities that RISs present to channel charting, particularly focusing on how RIS reconfiguration affects the learned low-dimensional representations. We focus on a contrastive learning framework with triplet loss to derive a channel chart through distance learning, and incorporate the RIS configuration information into the learning process, aiming to develop channel charts that are robust to changes in the RIS configuration. We also explore the potential for leveraging channel charts to inform RIS configuration, enabling applications where the channel chart is used to determine optimal RIS settings from a given codebook.