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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45237
    Prev
    Next
    INDEX
    Explanations

    In/Lie

    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
     ouder
    -0.08
     Brent
    -0.08
     Proms
    -0.08
     voldoen
    -0.08
     Isaac
    -0.07
     magnets
    -0.07
    asant
    -0.07
    Avg
    -0.07
     blackout
    -0.07
     avg
    -0.07
    POSITIVE LOGITS
     নিহ
    0.15
     заключается
    0.14
     darin
    0.12
     lies
    0.12
     nằm
    0.12
     reside
    0.11
     lie
    0.11
     হলো
    0.09
     resides
    0.09
    所在
    0.09
    Activations Density 0.110%

    No Known Activations