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

    Neuronpedia

    Jacobian LensNEW
    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. 68900
    Prev
    Next
    INDEX
    Explanations

    Idols, heroes, and fans

    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
    ّى
    -0.08
     overse
    -0.08
    جلس
    -0.08
    -zone
    -0.08
    754
    -0.07
     vlan
    -0.07
     leased
    -0.07
     diseñ
    -0.07
    חרי
    -0.07
     acetate
    -0.07
    POSITIVE LOGITS
     idol
    0.10
     fandom
    0.10
     admiration
    0.10
     admirer
    0.10
     поклон
    0.10
     ആരാധ
    0.09
    .youtube
    0.09
     idols
    0.09
     mentors
    0.09
     admire
    0.09
    Activations Density 0.083%

    No Known Activations