AbstractThis paper investigates the suitability and interpretability of a data‐driven deep learning algorithm for multi cross sectional overstrength factor prediction. For this purpose, we first compile datasets consisting of experiments from literature on the overstrength factor of circular, rectangular and square hollow sections as well as I‐ and H‐sections. We then propose a novel multi‐head encoder architecture consisting of three input heads (one head per section type represented by respective features), a shared embedding layer as well as a subsequent regression tail for predicting the overstrength factor. By construction, this multi‐head architecture simultaneously allows for (i) the exploration of the nonlinear embedding of different cross‐sectional profiles towards the overstrength factor within the shared layer, and (ii) a forward prediction of the overstrength factor given profile features. Our framework enables for the first time an exploration of cross‐section similarity w.r.t. the overstrength factor across multiple sections and hence provides new domain insights in bearing capacities of steel cross‐sections, a much wider data exploration, since the encoder‐regressor can serve as meta model predictor. We demonstrate the quality of the predictive capabilities of the model and gain new insights of the latent space of different steel sections w.r.t. the overstrength factor. Our proposed method can easily be transferred to other multi‐input problems of Scientific Machine Learning.