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. 60844
    Prev
    Next
    INDEX
    Explanations

    fashion and beauty

    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
    Measures
    -0.09
     betrieben
    -0.08
    Non
    -0.08
    HOST
    -0.08
    Density
    -0.08
    Destination
    -0.07
    Integration
    -0.07
    Interstitial
    -0.07
    ാവ
    -0.07
     macros
    -0.07
    POSITIVE LOGITS
     가진
    0.09
     vc
    0.08
     quân
    0.08
     həyat
    0.08
     conséquences
    0.08
    очке
    0.08
     처음
    0.08
     education
    0.08
     교육
    0.08
     lombok
    0.08
    Activations Density 0.055%

    No Known Activations