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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9248
    Prev
    Next
    INDEX
    Explanations

    _METHOD

    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
     dav
    -0.08
     Kamp
    -0.08
    -ass
    -0.08
     ail
    -0.07
     Zam
    -0.07
     Isa
    -0.07
     PLAYER
    -0.07
     A
    -0.07
     kampen
    -0.07
     fakt
    -0.07
    POSITIVE LOGITS
    Triggered
    0.08
     begrü
    0.08
    	Intent
    0.08
    еж
    0.08
    Clicked
    0.08
    ੱਚ
    0.08
     Optimization
    0.08
    	On
    0.08
    ==='
    0.07
     prer
    0.07
    Activations Density 0.001%

    No Known Activations