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. 53086
    Prev
    Next
    INDEX
    Explanations

    reach

    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
     rupa
    -0.08
    amor
    -0.08
    woh
    -0.07
    joe
    -0.07
    hattan
    -0.07
    akin
    -0.07
    Rsp
    -0.07
    cir
    -0.07
    써
    -0.07
    cus
    -0.07
    POSITIVE LOGITS
     fruition
    0.08
    足
    0.08
    .sm
    0.08
     hay
    0.07
    达
    0.07
     Ki
    0.07
    दी
    0.07
    果
    0.07
     daju
    0.07
    央
    0.07
    Activations Density 0.022%

    No Known Activations