© 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. 69590
    Prev
    Next
    INDEX
    Explanations

    Finance/Game Context

    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
    准
    -0.07
    -0.07
    Psi
    -0.06
     dop
    -0.06
    Delta
    -0.06
    Color
    -0.06
    Dé
    -0.06
    準
    -0.06
     સિ
    -0.06
     hyd
    -0.06
    POSITIVE LOGITS
    ாம்
    0.09
     বাংলাদেশ
    0.09
     intermediary
    0.09
     amazingly
    0.09
     uki
    0.09
     Pitts
    0.09
    ")){↵
    0.09
     сада
    0.09
     kenya
    0.09
     bansa
    0.08
    Activations Density 0.000%

    No Known Activations