© 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. 51888
    Prev
    Next
    INDEX
    Explanations

    say 165

    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
     unhas
    -0.10
    เอ็ม
    -0.09
    彩票站
    -0.09
     หวย
    -0.08
    hnten
    -0.08
    LOGY
    -0.08
     процедура
    -0.08
     магазине
    -0.08
    017
    -0.08
    quid
    -0.08
    POSITIVE LOGITS
    165
    0.09
    panel
    0.09
    Dry
    0.07
    74
    0.07
     Dry
    0.07
     destinat
    0.07
    Panel
    0.07
     요
    0.07
    意思
    0.07
     panel
    0.07
    Activations Density 0.001%

    No Known Activations