© 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. 16613
    Prev
    Next
    INDEX
    Explanations

    postings

    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
     وير
    -0.10
     mellitus
    -0.09
     kwe
    -0.09
     جوان
    -0.09
    ัฒ
    -0.09
     odnosno
    -0.09
    яса
    -0.08
     Metz
    -0.08
     ځواک
    -0.08
     אחרים
    -0.08
    POSITIVE LOGITS
    :
    0.16
    ：
    0.11
    :↵
    0.10
    :"
    0.10
     Presented
    0.10
    :true
    0.09
    :J
    0.09
    :↵↵
    0.09
    :no
    0.09
    :'
    0.09
    Activations Density 0.159%

    No Known Activations