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. 111983
    Prev
    Next
    INDEX
    Explanations

    Script

    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
     Zut
    -0.09
     zut
    -0.08
     Andaluc
    -0.08
     Asper
    -0.08
    াখ
    -0.08
     IU
    -0.08
     Lewis
    -0.08
    asured
    -0.07
    igram
    -0.07
     vo
    -0.07
    POSITIVE LOGITS
     kidd
    0.08
    ୀ
    0.08
    /
    0.07
     veh
    0.07
    /Web
    0.07
     Dire
    0.07
     sle
    0.07
     Sant
    0.07
     cele
    0.07
     interior
    0.07
    Activations Density 0.002%

    No Known Activations