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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 120487
    Prev
    Next
    INDEX
    Explanations

    testing

    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
     tribe
    -0.08
     apost
    -0.08
     Huffington
    -0.08
     муд
    -0.07
     شهد
    -0.07
     élégant
    -0.07
     substrate
    -0.07
     glam
    -0.07
     offences
    -0.07
    -smart
    -0.07
    POSITIVE LOGITS
    Testing
    0.11
     diu
    0.11
     Testing
    0.10
     getestet
    0.10
     Tested
    0.10
     efficacy
    0.09
    Tester
    0.09
     Tester
    0.09
    是否
    0.09
     tested
    0.09
    Activations Density 0.088%

    No Known Activations