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. 60942
    Prev
    Next
    INDEX
    Explanations

    processing

    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
     capelli
    -0.08
     luk
    -0.08
     Hanoi
    -0.07
     hilo
    -0.07
    Hair
    -0.07
     Hank
    -0.07
    .C
    -0.07
    깔
    -0.07
     Hair
    -0.07
     വൈ
    -0.07
    POSITIVE LOGITS
     personenbez
    0.09
     comply
    0.09
     outsourced
    0.09
    违法
    0.08
     GDPR
    0.08
     justice
    0.08
     compliant
    0.08
     outsourcing
    0.08
     件
    0.08
     కార్యక
    0.08
    Activations Density 0.005%

    No Known Activations