© 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. 23-RESID-POST-AA
    11. 97236
    Prev
    Next
    INDEX
    Explanations

    insults

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ㅎㅎ
    -0.09
     اللقاء
    -0.09
     সন্ধ
    -0.08
    超级
    -0.08
    Ồ
    -0.08
     😊
    -0.08
     عدة
    -0.08
     необы
    -0.08
     כמובן
    -0.08
     adventurous
    -0.08
    POSITIVE LOGITS
     pathetic
    0.24
     asshole
    0.19
     idiots
    0.19
     assh
    0.19
     incompet
    0.18
     bullshit
    0.18
     mierda
    0.18
     worthless
    0.18
     долбо
    0.18
     stupidity
    0.17
    Activations Density 0.134%

    No Known Activations