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. 15-RESID-POST-AA
    6. 19112
    Prev
    Next
    INDEX
    Explanations

    HTML elements

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     culminating
    -0.08
     disg
    -0.08
     exotic
    -0.08
     stemming
    -0.08
     ধর্ম
    -0.08
     brevet
    -0.08
     promulg
    -0.08
     tentative
    -0.08
     Blum
    -0.08
     diskr
    -0.07
    POSITIVE LOGITS
     HTMLElement
    0.22
    HTMLElement
    0.20
    DOMContent
    0.15
     $("#
    0.15
     $('#
    0.14
    <HTMLInput
    0.14
     DOM
    0.14
    <HTML
    0.14
     textarea
    0.14
    =document
    0.14
    Activations Density 0.015%

    No Known Activations