The abrupt onset of a novel event captures attention away from, and disrupts, ongoing task performance. Less obvious is that intentional task switching compares with novelty-induced behavioral distraction. Here we explore the hypothesis that intentional task switching and attentional capture by a novel distracter both activate a common neural network involved in processing contextual novelty [Barcelo, F., Periáñez, J. A., & Knight, R. T. Think differently: A brain orienting response to task novelty. NeuroReport, 13, 1887-1892, 2002.]. Event-related potentials were recorded in two task-cueing paradigms while 16 subjects sorted cards following either two (color or shape; two-task condition) or three (color, shape, or number; three-task condition) rules of action. Each card was preceded by a familiar tone cueing the subject either to switch or to repeat the previous rule. Novel sound distracters were interspersed in one of two blocks of trials in each condition. Both novel sounds and task-switch cues impaired responses to the following visual target. Novel sounds elicited novelty P3 potentials with their usual peak latency and frontal-central scalp distribution. Familiar tonal switch cues in the three- and two-task conditions elicited brain potentials with a similar latency and morphology as the novelty P3, but with relatively smaller amplitudes over frontal scalp regions. Covariance and principal component analyses revealed a sustained frontal negative potential that was distorting concurrent novelty P3 activity to the tonal switch cues. When this frontal negativity was statistically removed, P3 potentials to novel sounds and task-switch cues showed similar scalp topographies. The degree of activation in the novelty P3 network seemed to be a function of the information (entropy) conveyed by the eliciting stimulus for response selection, over and above its relative novelty, probability of occurrence, task relevance, or feedback value. We conclude that novelty P3 reflects transient activation in a neural network involved in updating task set information for goal-directed action selection and might thus constitute one key element in a central bottleneck for attentional control.