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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 26670
    Prev
    Next
    INDEX
    Explanations

    lattice points

    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
     behavioral
    -0.09
     oscill
    -0.08
     beh
    -0.08
     log
    -0.08
     사업
    -0.08
     compound
    -0.07
     reproduce
    -0.07
     password
    -0.07
    売
    -0.07
     exponential
    -0.07
    POSITIVE LOGITS
     gcd
    0.14
     Jar
    0.09
     संख्या
    0.09
    ագիտական
    0.08
    -grid
    0.08
    /grid
    0.08
     Gun
    0.08
    зер
    0.08
    oint
    0.08
     QPoint
    0.08
    Activations Density 0.016%

    No Known Activations