© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 99462
    Prev
    Next
    INDEX
    Explanations

    relative key in music

    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
    phal
    -0.09
    isa
    -0.08
    linger
    -0.08
     Laws
    -0.08
    isco
    -0.08
     рев
    -0.08
     tendencia
    -0.07
     thiên
    -0.07
    Sta
    -0.07
     imply
    -0.07
    POSITIVE LOGITS
     سار
    0.08
     ಮೆ
    0.08
     accessibles
    0.08
     després
    0.08
     strumenti
    0.08
    	short
    0.08
     nakon
    0.08
     ಸಾಧ
    0.08
    0.08
    共享
    0.07
    Activations Density 0.000%
    No Known Activations