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. 117301
    Prev
    Next
    INDEX
    Explanations

    Even numbers

    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
    cura
    -0.08
    صي
    -0.08
     Gabri
    -0.07
    .title
    -0.07
     kine
    -0.07
     gf
    -0.07
     Rafa
    -0.07
     särsk
    -0.07
    ытай
    -0.07
    (image
    -0.07
    POSITIVE LOGITS
     ändå
    0.10
     ngunit
    0.10
    लेकिन
    0.09
     लेकिन
    0.09
    但是
    0.09
    -but
    0.09
     dennoch
    0.09
     પરંતુ
    0.09
    ولكن
    0.08
     ஆனால்
    0.08
    Activations Density 0.216%

    No Known Activations