Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97082
    Prev
    Next
    INDEX
    Explanations

    k

    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
     ziv
    -0.09
     Zee
    -0.09
     žád
    -0.09
     yung
    -0.09
    ്യേ
    -0.08
     ileg
    -0.08
     ضع
    -0.08
     Kann
    -0.08
     Kasi
    -0.08
    nä
    -0.08
    POSITIVE LOGITS
    inerja
    0.17
    egiatan
    0.16
    umpulan
    0.15
    aryawan
    0.15
    eterangan
    0.15
    embangkan
    0.15
    unci
    0.14
    oneksi
    0.14
    ucing
    0.14
    emenangan
    0.14
    Activations Density 0.002%

    No Known Activations