Typically, for instance in test taking, the 95th percentile refers to the bottom 95%In the SD context, if it's a normal distribution then 68% of results fall within 1 SD of the mean and 95% within 2 SD of the mean. Which is why some people refer to lower (or higher) values more than 2 SD from the mean as the 95th percentile. In this case you can knock off 5% outliers by only considering cases within 2 SD of the mean- if it's a normal distribution. If it's an abnormal distribution then all bets are off.
"... They ne'er cared for us
yet: suffer us to famish, and their store-houses
crammed with grain; make edicts for usury, to
support usurers; repeal daily any wholesome act
established against the rich, and provide more
piercing statutes daily, to chain up and restrain
the poor. If the wars eat us not up, they will; and
there's all the love they bear us."
-- Shakespeare: Coriolanus, Act 1, scene 1
