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. 108
    Prev
    Next
    INDEX
    Explanations

    since

    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
     ability
    -0.08
    /path
    -0.08
     respective
    -0.07
     appropriate
    -0.07
     corresponding
    -0.07
    /
    -0.07
     potentially
    -0.07
     apropi
    -0.07
    /F
    -0.07
     auala
    -0.07
    POSITIVE LOGITS
    since
    0.13
     since
    0.11
    the
    0.10
    also
    0.10
    _since
    0.10
     ity
    0.09
     saboda
    0.09
    :]↵
    0.09
    .
    0.09
    Since
    0.09
    Activations Density 0.022%

    No Known Activations