© 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. 15-RESID-POST-AA
    11. 16393
    Prev
    Next
    INDEX
    Explanations

    cities and towns

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     लगाने
    -0.08
    👏
    -0.08
     polyval
    -0.08
     photovolta
    -0.07
    読む
    -0.07
     Appreci
    -0.07
    ateľ
    -0.07
     marginal
    -0.07
     رفع
    -0.07
     مثبت
    -0.07
    POSITIVE LOGITS
    ™
    0.11
     നഗ
    0.10
     bustling
    0.10
     നഗര
    0.10
     शहर
    0.10
     town
    0.10
     गाव
    0.09
     города
    0.09
     phố
    0.09
     enchanted
    0.09
    Activations Density 0.053%

    No Known Activations