© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 96720
    Prev
    Next
    INDEX
    Explanations

    code-related phrases

    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
    /k
    -0.08
     rinc
    -0.07
    ник
    -0.07
    ника
    -0.07
     hover
    -0.07
    _k
    -0.07
    ienia
    -0.07
     چه
    -0.07
     hyperlinks
    -0.07
    -stock
    -0.07
    POSITIVE LOGITS
     Absolutely
    0.08
     Plaint
    0.08
    ీజ్
    0.08
    皇家
    0.08
     kirjut
    0.08
    uger
    0.08
     puzzle
    0.08
     দক্ষিণ
    0.08
    ,res
    0.07
    蒙古
    0.07
    Activations Density 0.000%

    No Known Activations