© 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 EvalsExportsinterp-engineNEWAPI 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. 63123
    Prev
    Next
    INDEX
    Explanations

    love

    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
    杆
    -0.09
    -Key
    -0.09
     Asamblea
    -0.08
     Chevron
    -0.08
     Stool
    -0.08
     afval
    -0.08
     Accountant
    -0.08
     Quartz
    -0.08
     methane
    -0.08
     Fukushima
    -0.08
    POSITIVE LOGITS
    爱情
    0.26
    恋
    0.21
     romant
    0.21
     romantic
    0.20
     románt
    0.19
     প্রেম
    0.19
     प्रेम
    0.18
    戀
    0.18
     காத
    0.18
    情侣
    0.18
    Activations Density 0.203%

    No Known Activations