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. 42014
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    dates
    -0.08
     uncovered
    -0.07
     ఖ
    -0.07
     or
    -0.07
    .up
    -0.07
    (coords
    -0.07
    BJ
    -0.07
     ná
    -0.07
    -0.07
    R
    -0.07
    POSITIVE LOGITS
     aman
    0.08
    añas
    0.08
     يح
    0.08
     gana
    0.08
    \\.
    0.08
     leng
    0.08
    יימ
    0.08
    оми
    0.07
     QUICK
    0.07
     snippet
    0.07
    Activations Density 0.000%

    No Known Activations