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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 120241
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    mind
    -0.08
    ziy
    -0.08
     delt
    -0.07
    cession
    -0.07
    Mind
    -0.07
     Stu
    -0.07
     Zag
    -0.07
     पहुंच
    -0.07
     homogeneous
    -0.07
    .Role
    -0.07
    POSITIVE LOGITS
    ۱
    0.08
     Infragistics
    0.08
     മണിക്ക
    0.08
    urve
    0.08
    Gujarati
    0.08
    XB
    0.08
    ур
    0.07
    unprocessable
    0.07
    נד
    0.07
     cari
    0.07
    Activations Density 0.000%

    No Known Activations