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. 112095
    Prev
    Next
    INDEX
    Explanations

    restriction

    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
     Gide
    -0.08
    수를
    -0.07
     fut
    -0.07
     минимум
    -0.07
    수가
    -0.07
    수
    -0.07
     axe
    -0.07
    mol
    -0.07
     enf
    -0.07
     gel
    -0.07
    POSITIVE LOGITS
     사항
    0.11
    事項
    0.10
     دست
    0.09
    사항
    0.08
    兑换
    0.08
     sév
    0.08
     NP
    0.08
     ij
    0.07
     upt
    0.07
     बस
    0.07
    Activations Density 0.011%

    No Known Activations