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. 98607
    Prev
    Next
    INDEX
    Explanations

    mixed content

    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
    uab
    -0.08
    _dom
    -0.08
    ítica
    -0.08
    vyk
    -0.07
    Uf
    -0.07
    leid
    -0.07
     yc
    -0.07
     domini
    -0.07
    ీలో
    -0.07
    uin
    -0.07
    POSITIVE LOGITS
    oph
    0.08
    ões
    0.08
    'art
    0.07
     él
    0.07
     Bitcoins
    0.07
    ophageal
    0.07
    ત
    0.07
    .art
    0.07
     dood
    0.07
    ão
    0.07
    Activations Density 0.019%

    No Known Activations