Preparation for a switch in task was manipulated using two types of switch cues: ‘switchaway’from the previous task-set and ‘switch-to’ a different task-set. Increasing cue–stimulus interval resulted in a reduction in reaction time switch cost for switch-to trials only. Cuelocked difference waveforms for both switch-to and switch-away trials showed a large, broad differential positivity, relative to repeat waveforms. However, the later part of the differential positivity was significantly reduced on switch-away trials. A differential positivity then emerged after stimulus onset for switch-away trials only. This suggests that, with a long cue–stimulus interval, the new task-set was implemented before stimulus onset for switch-to trials, whereas on switch-away trials this process was delayed until after stimulus onset leading to increased switch cost. These results demonstrate dissociable effects of switching away from the current task-set and switching to the upcoming task-set and support the interpretation that the differential positivity observed for switch-to trials reflects processes associated with anticipatory task-set reconfiguration.