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. 112447
    Prev
    Next
    INDEX
    Explanations

    math problems

    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
    leder
    -0.08
    .Test
    -0.08
    glas
    -0.07
    hias
    -0.07
     Paste
    -0.07
    jeve
    -0.07
     avan
    -0.07
     jama
    -0.07
    mys
    -0.07
    .ACT
    -0.07
    POSITIVE LOGITS
    ៗ
    0.08
     توزي
    0.08
     Kö
    0.08
    інші
    0.08
     ретінде
    0.07
     sā
    0.07
     moreover
    0.07
     причем
    0.07
     توګه
    0.07
    ूपी
    0.07
    Activations Density 0.062%

    No Known Activations