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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119982
    Prev
    Next
    INDEX
    Explanations

    $

    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
    атика
    -0.08
     Twins
    -0.07
     daughters
    -0.07
    reden
    -0.07
    feit
    -0.07
     generator
    -0.07
    chai
    -0.07
    ए
    -0.07
    iração
    -0.07
    ผล
    -0.07
    POSITIVE LOGITS
     prä
    0.09
     précis
    0.09
     Prä
    0.09
    <const
    0.08
    .databinding
    0.08
    _PORT
    0.08
     præ
    0.07
     Bayern
    0.07
     constexpr
    0.07
     precisa
    0.07
    Activations Density 0.001%

    No Known Activations