Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 170
    Prev
    Next
    INDEX
    Explanations

    ellipses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     por
    -0.08
     of
    -0.07
    -dependent
    -0.07
     alg
    -0.07
    -0.07
    -ad
    -0.07
     использу
    -0.07
     can
    -0.07
     by
    -0.07
     bilm
    -0.07
    POSITIVE LOGITS
     preceded
    0.09
     stedet
    0.09
     primul
    0.09
     luogo
    0.09
    。而
    0.09
    。所以
    0.09
    。因此
    0.09
     Essentially
    0.08
     lugar
    0.08
    that's
    0.08
    Activations Density 0.005%

    No Known Activations