© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30257
    Prev
    Next
    INDEX
    Explanations

    html forms

    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
     Zuschauer
    -0.09
     Perr
    -0.09
     GPUs
    -0.08
    .bluetooth
    -0.08
     microorganisms
    -0.08
    abit
    -0.08
    억
    -0.08
    Substring
    -0.08
     Flugh
    -0.08
     cinemat
    -0.08
    POSITIVE LOGITS
     formulário
    0.19
     formulaire
    0.19
     formulario
    0.17
    フォーム
    0.16
     Formular
    0.15
     enctype
    0.15
    <form
    0.14
     formular
    0.14
    Formulario
    0.14
    =form
    0.14
    Activations Density 0.022%

    No Known Activations