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. 113062
    Prev
    Next
    INDEX
    Explanations

    Parentheses and equals signs

    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
    elay
    -0.08
     STAR
    -0.08
    :hover
    -0.07
    _overlay
    -0.07
     stare
    -0.07
    /rss
    -0.07
    @Post
    -0.07
    群
    -0.07
     sead
    -0.07
    !important
    -0.07
    POSITIVE LOGITS
    是多少
    0.12
     calculated
    0.09
     hidrául
    0.08
     কত
    0.08
     কাট
    0.08
     দশ
    0.08
     deducted
    0.08
    Calculate
    0.08
     inches
    0.08
     рассчиты
    0.08
    Activations Density 0.022%

    No Known Activations