© 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. 108674
    Prev
    Next
    INDEX
    Explanations

    loor

    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
    bei
    -0.09
     Rousse
    -0.08
     conserved
    -0.08
    жава
    -0.08
    _routes
    -0.08
    ussi
    -0.08
    čine
    -0.08
    akte
    -0.08
    DO
    -0.07
    illé
    -0.07
    POSITIVE LOGITS
     سن
    0.08
     fed
    0.08
     decade
    0.08
     cen
    0.08
    ▒
    0.07
     Towers
    0.07
     fo
    0.07
     blocks
    0.07
     tany
    0.07
     [[
    0.07
    Activations Density 0.003%

    No Known Activations