© 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 EvalsExportsinterp-engineNEWAPI 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. 70908
    Prev
    Next
    INDEX
    Explanations

    game winning/losing states

    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
     המ
    -0.08
     פנים
    -0.08
     לה
    -0.08
     ʻ
    -0.08
     Inches
    -0.08
     Yee
    -0.08
    יבים
    -0.08
    _xlim
    -0.08
     סע
    -0.08
     Lorem
    -0.07
    POSITIVE LOGITS
     defeat
    0.09
     જીત
    0.09
     выиг
    0.09
     greed
    0.08
     mex
    0.08
     bewertet
    0.08
     deny
    0.08
     xor
    0.08
     मतदान
    0.08
     defeating
    0.08
    Activations Density 0.004%

    No Known Activations