I have been thinking about this one and here is an idea.
1) Time and cross-sectionally demean your data. How to do this is shown here. SAS/ETS(R) 14.1 User's Guide You will likely want to use some form of PROC TIMESERIES or some PROC MEANS calls to do this.
2) Now that the data are "demeaned" a simple OLS estimate would give you your "Two-way FE" estimates. From here you could then extend this regression by using PROC REG or perhaps better, PROC GLMSELECT SAS/STAT(R) 14.1 User's Guide
and use whatever variable selection method you prefer. In essence, it would force FE into your model, with whatever final specification the algorithm chooses.
*would love to see some of your results.
Good luck-Ken