Objectives In cT1‐2N0, oral squamous cell carcinoma (OSCC) occult metastases are detected in 23%‐37% of cases. Sentinel lymph node biopsy (SLNB) was introduced in head and neck cancer as a minimally invasive alternative for an elective neck dissection in neck staging. Meta‐analyses of SLNB accuracy show heterogeneity in the existing studies for reference standards, imaging techniques and pathological examination. The aim of this study was to assess the sensitivity and negative predictive value (NPV) of the SLNB in detecting occult metastases in cT1‐2N0 OSCC in a well‐defined cohort. Design Retrospective study. The SLNB procedure consisted of lymphoscintigraphy, SPECT/CT‐scanning and gamma probe detection. Routine follow‐up was the reference standard for the SLNB negative neck. Histopathological examination of sentinel lymph nodes (SLN) consisted of step serial sectioning, haematoxylin‐eosin and cytokeratin AE1/3 staining. Setting Two comprehensive oncology centres. Participants A total of 91 consecutive patients with primary cT1‐2N0 OSCC treated by primary resection and neck staging by SLNB procedure between 2008 and 2016. Main outcome measures Sensitivity and negative predictive value. Results In all cases, SLNs were harvested. A total of 25 (27%) patients had tumour‐positive SLNs. The median follow‐up was 32 months (range 2‐104). Four patients were diagnosed with an isolated regional recurrence in the SLNB negative neck side resulting in an 85% sensitivity and a 94% NPV. Conclusion In our cohort, the SLNB detected occult metastases in early OSCC with 85% sensitivity and 94% NPV. This supports that SLNB is a reliable procedure for surgical staging of the neck in case of oral cT1‐2N0 SCC.