© 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. 78772
    Prev
    Next
    INDEX
    Explanations

    motivational quotes

    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
    .Ed
    -0.07
    执
    -0.07
    वें
    -0.07
     zeer
    -0.07
     सहाय
    -0.07
     paj
    -0.07
     veh
    -0.07
    Ed
    -0.07
    Assembler
    -0.07
     घोषित
    -0.07
    POSITIVE LOGITS
     lies
    0.11
    秘诀
    0.10
     النجاح
    0.09
    鍵
    0.09
     заключается
    0.09
     নিহ
    0.08
     tight
    0.08
     نجاح
    0.08
     وراء
    0.08
     segredo
    0.08
    Activations Density 0.034%

    No Known Activations