Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 77380
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    balances
    -0.09
     감
    -0.08
    -ready
    -0.08
     చెప్పారు
    -0.08
     noises
    -0.08
    über
    -0.08
     améric
    -0.08
    dados
    -0.08
    antly
    -0.08
    ROR
    -0.08
    POSITIVE LOGITS
    ଟ
    0.10
    -dimensional
    0.09
     leading
    0.08
    ಟ
    0.08
     Rubber
    0.08
     цикл
    0.07
    年前
    0.07
    -year
    0.07
     hari
    0.07
     taona
    0.07
    Activations Density 0.022%

    No Known Activations