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. 11-RESID-POST-AA
    6. 53957
    Prev
    Next
    INDEX
    Explanations

    axis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     युव
    -0.08
     uno
    -0.08
     reminders
    -0.08
     DAO
    -0.07
     error
    -0.07
     mod
    -0.07
     gritty
    -0.07
     सीम
    -0.07
     avoid
    -0.07
     beige
    -0.07
    POSITIVE LOGITS
     cylindrical
    0.10
     rotational
    0.10
    轴
    0.10
     цилинд
    0.09
    -axis
    0.09
    (axis
    0.09
     axis
    0.09
    (Qt
    0.09
     cilind
    0.09
    pendicular
    0.09
    Activations Density 0.014%

    No Known Activations