© 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. 23-RESID-POST-AA
    11. 51444
    Prev
    Next
    INDEX
    Explanations

    Gold/metal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spurs
    -0.09
     carav
    -0.08
     pele
    -0.08
     melt
    -0.08
    ро
    -0.07
     ron
    -0.07
     Eli
    -0.07
    ople
    -0.07
    สบ
    -0.07
    urve
    -0.07
    POSITIVE LOGITS
    金
    0.21
     金
    0.19
     금
    0.18
    금
    0.18
     ধ
    0.17
     ध
    0.17
     ધ
    0.16
     دھ
    0.16
     ਧ
    0.15
    ध
    0.15
    Activations Density 0.007%

    No Known Activations