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. 31
    Prev
    Next
    INDEX
    Explanations

    asy

    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
     HDD
    -0.09
    jenih
    -0.08
    editing
    -0.08
     airing
    -0.08
     Germ
    -0.08
    ovas
    -0.08
     আও
    -0.08
     vieler
    -0.08
     uwezo
    -0.08
    azvo
    -0.08
    POSITIVE LOGITS
    0.08
    .Runtime
    0.07
    dep
    0.07
    dup
    0.07
    փ
    0.07
    _graph
    0.07
     chang
    0.07
    keep
    0.07
     Runtime
    0.07
    _dep
    0.07
    Activations Density 0.001%

    No Known Activations