© 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. 65470
    Prev
    Next
    INDEX
    Explanations

    key

    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
     Suff
    -0.08
    ateur
    -0.08
     Watching
    -0.08
    ій
    -0.08
    891
    -0.07
    SCR
    -0.07
     outright
    -0.07
     stipend
    -0.07
     Gratis
    -0.07
     freien
    -0.07
    POSITIVE LOGITS
     takeaway
    0.12
    notes
    0.11
    appa
    0.09
    പ്പെട്ട
    0.09
    cloak
    0.08
    note
    0.08
    人物
    0.08
    stay
    0.08
     момен
    0.08
    时候
    0.08
    Activations Density 0.028%

    No Known Activations