© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 16259
    Prev
    Next
    INDEX
    Explanations

    frequent

    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
     overcame
    -0.07
     unscr
    -0.07
    anies
    -0.07
    aro
    -0.07
     overcome
    -0.07
     ech
    -0.07
     Lindsay
    -0.07
     ehd
    -0.07
     rescued
    -0.07
     Eva
    -0.07
    POSITIVE LOGITS
     frequent
    0.18
     frecuentes
    0.17
     Frequent
    0.16
     frecuente
    0.16
    頻
    0.15
    requent
    0.15
    频
    0.14
     frequ
    0.14
     fréqu
    0.14
     fréquence
    0.14
    Activations Density 0.082%

    No Known Activations