A timestep is one position or unrolled cell in a sequential model such as a recurrent neural network. It represents a point in the sequence where the model processes input, updates state, and passes information forward.
One "unrolled" cell within a recurrent neural network. For example, the following figure shows three timesteps (labeled with the subscripts t-1, t, and t+1): !Three timesteps in a recurrent neural network. The output of the first timestep becomes input to the second timestep. The output of the second timestep becomes input to the third timestep.