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

    Neuronpedia

    Jacobian LensNEW
    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. 11-RESID-POST-AA
    11. 112471
    Prev
    Next
    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elenium
    -0.09
    /security
    -0.09
    服务器
    -0.09
     প্রশাস
    -0.08
     leases
    -0.08
    .browser
    -0.08
     JFile
    -0.08
     servidores
    -0.08
    /browser
    -0.08
    ：http
    -0.08
    POSITIVE LOGITS
     lyrics
    0.18
    lyrics
    0.16
    歌词
    0.16
     गीत
    0.15
     Lyrics
    0.15
     verses
    0.14
    Lyrics
    0.14
    歌曲
    0.14
     lyric
    0.14
     vocals
    0.14
    Activations Density 0.017%

    No Known Activations