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. 112066
    Prev
    Next
    INDEX
    Explanations

    nad

    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
    pricht
    -0.09
    owitz
    -0.08
     Pregnancy
    -0.08
    allenge
    -0.08
    fik
    -0.08
     oneself
    -0.07
    ೊಳ
    -0.07
    anez
    -0.07
     పుర
    -0.07
     аз
    -0.07
    POSITIVE LOGITS
     cour
    0.09
     SIP
    0.08
    τοι
    0.08
    -source
    0.08
    ***
    0.08
    вой
    0.08
     fuentes
    0.08
     터
    0.07
     sources
    0.07
    /npm
    0.07
    Activations Density 0.000%

    No Known Activations