Somatodendritic missorting of the axonal protein TAU is a hallmark of Alzheimer’s disease and related tauopathies. Cultured rodent primary neurons and iPSC-derived neurons are often used for studying mechanisms of neuronal polarity, including TAU trafficking. However, these models are expensive, time-consuming and/or require the sacrification of animals. In this study, we show that neurons derived from SH-SY5Y neuroblastoma cells, generated with a RA/BDNF-based differentiation procedure, are suitable for investigating axonal TAU sorting. These SH-SY5Y-derived neurons show pronounced neuronal polarity, axodendritic outgrowth, expression of the neuronal maturation markers TAU and MAP2, and, importantly, efficient axonal sorting of endogenous and transfected human wild type TAU. By using SH-SY5Y-derived neurons and mouse primary neurons, we demonstrate that axonal TAU enrichment requires the presence of the TAU C-terminal half, as a truncated C-terminus-lacking construct (N-term-TAUHA) is localized in the soma, where it accumulates. Moreover, SH-SY5Y-derived neurons do not show classical axon initial segment (AIS) formation, indicated by the lack of Ankyrin G (ANKG) enrichment at the proximal axon, which suggests that successful axonal TAU sorting is independent of complete AIS formation. Taken together, our results suggest i) that SH-SY5Y-derived neurons are a valuable human neuronal model for studying TAU sorting, which is readily accessible at low cost and without animal need, and that ii) the mechanisms of axonal TAU targeting require the TAU C-terminal half but no ANKG enrichment at the proximal axon.