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. 67300
    Prev
    Next
    INDEX
    Explanations

    matrix inversion and code

    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
     ಹೊಸ
    -0.08
     പുതിയ
    -0.08
    st
    -0.08
     uuden
    -0.08
     New
    -0.07
     രണ്ട
    -0.07
     नवीन
    -0.07
    New
    -0.07
    irma
    -0.07
     নতুন
    -0.07
    POSITIVE LOGITS
     admittedly
    0.14
     notoriously
    0.12
     unfortunately
    0.10
     allerdings
    0.10
     simplistic
    0.09
    虽
    0.09
     relied
    0.09
     horribly
    0.09
     cumbersome
    0.09
     drawback
    0.09
    Activations Density 0.049%

    No Known Activations