Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58665
    Prev
    Next
    INDEX
    Explanations

    arrogance/narcissism

    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
     heartbreaking
    -0.09
    лаб
    -0.08
     genel
    -0.08
     වන
    -0.08
     unsubscribe
    -0.08
    	Spring
    -0.08
    urrent
    -0.08
     heartbreak
    -0.08
     stok
    -0.08
     Keeping
    -0.08
    POSITIVE LOGITS
     arrog
    0.18
     arrogance
    0.17
     arrogant
    0.16
     অহ
    0.15
     brag
    0.14
     narciss
    0.13
     boasting
    0.12
     자신
    0.12
     দাবি
    0.12
     claimed
    0.12
    Activations Density 0.099%

    No Known Activations