下記のコードによりtf-idf計算自体は(おそらく)出来ているとは思うのですが、この先のtf-idf値の高い単語を表示する方法が分かりません。
どなたかご教授いただけると幸いです。

ソースコード

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.decomposition import TruncatedSVD
from sklearn.preprocessing import Normalizer

def tf(doc):
    vectorizer = CountVectorizer(token_pattern=u'(?u)\\b\\w+\\b')
    features = vectorizer.fit_transform(doc)
    terms = vectorizer.get_feature_names()

    return features, terms

def tfidf(docs_list):

    vectorizer = TfidfVectorizer(min_df=1, max_df=50, token_pattern=u'(?u)\\b\\w+\\b')
    features = vectorizer.fit_transform(docs_list)
    terms = vectorizer.get_feature_names()

    return features, terms

def reduction(x, dim=10):

    '''
    dimensionality reduction using LSA
    '''
    lsa = TruncatedSVD()
    x = lsa.fit_transform(x)
    x = Normalizer(copy=False).fit_transform(x)

    return x

if __name__ == '__main__':
    docs_list = [clu1,clu2,clu3,clu4,clu5]
    docs_list = [' '.join(d) for d in docs_list]
    features, terms = tfidf(docs_list)
    features, terms = tfidf(docs_list)
    features = reduction(features, dim=2)