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. 58701
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
     dịka
    -0.08
     Consultancy
    -0.08
    unuz
    -0.08
    обще
    -0.08
    startup
    -0.08
    ху
    -0.07
     bitcoin
    -0.07
    რმ
    -0.07
    (lst
    -0.07
    .gf
    -0.07
    POSITIVE LOGITS
     Shannon
    0.08
    $_
    0.07
    plus
    0.07
    _{\
    0.07
     sn
    0.07
     Kyle
    0.07
    $email
    0.07
     coherence
    0.07
     הז
    0.07
    ory
    0.07
    Activations Density 0.093%

    No Known Activations