Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 76711
    Prev
    Next
    INDEX
    Explanations

    make

    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
     triun
    -0.09
     balconies
    -0.08
    อด
    -0.08
    霸王
    -0.08
    (Some
    -0.08
    privation
    -0.07
    _pas
    -0.07
    vere
    -0.07
    bur
    -0.07
     migraines
    -0.07
    POSITIVE LOGITS
     bim
    0.09
     рабоч
    0.08
     kendaraan
    0.08
     Currency
    0.08
     langue
    0.08
     customizable
    0.08
     currency
    0.07
     gebra
    0.07
     eléctrico
    0.07
    Utf
    0.07
    Activations Density 0.000%

    No Known Activations