© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 113496
    Prev
    Next
    INDEX
    Explanations

    shot

    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
    €/
    -0.08
    োন
    -0.07
     participar
    -0.07
     abst
    -0.07
     ficar
    -0.07
    $p
    -0.07
    feel
    -0.07
     ולכן
    -0.07
    מצא
    -0.07
     workforce
    -0.07
    POSITIVE LOGITS
    灯
    0.09
     lush
    0.09
     चम
    0.09
     화면
    0.09
     появляется
    0.08
     Vera
    0.08
     bustling
    0.08
     gle
    0.08
     sleek
    0.08
     cinematic
    0.08
    Activations Density 0.017%

    No Known Activations