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. 77422
    Prev
    Next
    INDEX
    Explanations

    My

    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
     startling
    -0.08
     кнопку
    -0.08
    fert
    -0.08
    zos
    -0.08
     veto
    -0.07
    ճ
    -0.07
     Vet
    -0.07
    irical
    -0.07
     사용할
    -0.07
     differentiation
    -0.07
    POSITIVE LOGITS
    MC
    0.10
    _MC
    0.09
    ;
    ↵
    ↵
    0.08
    快
    0.07
     intimately
    0.07
     cerita
    0.07
     Sie
    0.07
    mc
    0.07
    走势
    0.07
     boyunca
    0.07
    Activations Density 0.002%

    No Known Activations