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. 77392
    Prev
    Next
    INDEX
    Explanations

    друг

    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
    wes
    -0.08
     noma
    -0.08
    .om
    -0.08
     Zij
    -0.07
     Nur
    -0.07
    (CG
    -0.07
    ਜ਼
    -0.07
     om
    -0.07
    ilty
    -0.07
     Get
    -0.07
    POSITIVE LOGITS
     пр
    0.08
     solace
    0.07
    ಾಟ
    0.07
    �ી
    0.07
     androidx
    0.07
     मध्ये
    0.07
     Party
    0.07
    เล
    0.07
    που
    0.07
     recuerdos
    0.07
    Activations Density 0.001%

    No Known Activations