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. 23-RESID-POST-AA
    6. 130987
    Prev
    Next
    INDEX
    Explanations

    can

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     four
    -0.10
     five
    -0.10
     three
    -0.10
    three
    -0.10
    two
    -0.10
     two
    -0.10
     six
    -0.10
     one
    -0.10
     some
    -0.10
     eight
    -0.10
    POSITIVE LOGITS
     involve
    0.13
     contain
    0.11
     contribute
    0.10
     comprise
    0.10
     possess
    0.09
     garnered
    0.09
     bevatten
    0.08
     involving
    0.08
     yield
    0.08
     Taken
    0.08
    Activations Density 0.058%

    No Known Activations