© 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. 23-RESID-POST-AA
    11. 97661
    Prev
    Next
    INDEX
    Explanations

    ö

    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
    વ્ય
    -0.08
    देख
    -0.08
    είο
    -0.08
     voilà
    -0.07
     petition
    -0.07
    зар
    -0.07
    essment
    -0.07
     permalink
    -0.07
     सारी
    -0.07
     élect
    -0.07
    POSITIVE LOGITS
    sterreich
    0.11
    rebro
    0.09
     라
    0.09
    stra
    0.08
    vers
    0.08
     BAY
    0.07
    RESH
    0.07
     ב
    0.07
    ירת
    0.07
    Src
    0.07
    Activations Density 0.000%

    No Known Activations