Abstract This study aimed to evaluate the impact of antenatal corticosteroid (ACS) administration prior to delivery on neonatal outcomes in extreme preterm neonates delivered between 21 and 23 weeks of gestation. This retrospective cohort study used data from the National Center for Health Statistics Vital Statistics database. Linked birth and infant death data files from 2015 to 2021 were included in the analysis. The study included singleton, nonanomalous pregnancies that were delivered between 21 and 24 weeks of gestation. Analysis was limited to births with known ACS status. The outcomes of interest were infant mortality, 5-minute Apgar score < 6, and neonatal intensive care unit admission. Univariate analysis was performed to determine the association between exposure and outcome. Logistic regression analysis was performed to determine the association, adjusting for potential confounders. There were 50,671 births included in the analysis. In this group, 15,601 (31%) received ACS prior to delivery. ACS administration prior to delivery was associated with lower neonatal death rate between 21 and 24 weeks (32.9 vs. 56.1%, p < 0.0001, adjusted odds ratio [aOR]: 0.53 [0.51–0.56]). Sub-analysis based on delivery at each gestational week demonstrated a protective effect at 21 weeks (70.1 vs. 80.7%, p = 0.001, aOR: 0.56 [0.34–0.91]); at 22 weeks (54.1 vs. 75.9%, aOR: 0.40 [0.35–0.47]); at 23 weeks (39.1 vs. 50.9%, aOR: 0.65, aOR [0.61–0.70]); and at 24 weeks (24.6 vs. 30.1%, aOR: 0.78 [0.73–0.83]). ACS administration in extreme preterm neonates born between 21 and 24 weeks was associated with improved survival.