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. 105924
    Prev
    Next
    INDEX
    Explanations

    Period

    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
     físicas
    -0.09
     teammate
    -0.08
     grassroots
    -0.08
     salesperson
    -0.08
     famously
    -0.08
    ittance
    -0.08
     fundamentally
    -0.08
    _IMAGES
    -0.08
    -assets
    -0.07
    enet
    -0.07
    POSITIVE LOGITS
     দেখি
    0.09
     pretend
    0.08
     pretending
    0.07
     Scha
    0.07
     করি
    0.07
     Sant
    0.07
     یعنی
    0.07
     gerecht
    0.07
     કરીએ
    0.07
    .UTF
    0.07
    Activations Density 0.100%

    No Known Activations