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. 42097
    Prev
    Next
    INDEX
    Explanations

    simpsons

    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
    inut
    -0.08
    (loss
    -0.08
     صاف
    -0.08
    య
    -0.08
    가
    -0.08
    โดย
    -0.08
     مخت
    -0.07
    rast
    -0.07
     Definit
    -0.07
    onya
    -0.07
    POSITIVE LOGITS
    487
    0.09
    382
    0.08
     Olive
    0.08
     VARCHAR
    0.08
     весьма
    0.08
     vell
    0.08
    942
    0.08
    488
    0.07
     pilgrimage
    0.07
     MLA
    0.07
    Activations Density 0.002%

    No Known Activations