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. 112044
    Prev
    Next
    INDEX
    Explanations

    HTML input fields and CSS

    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
     vaccine
    -0.08
    	web
    -0.08
    /errors
    -0.07
     évent
    -0.07
     kiss
    -0.07
     bölg
    -0.07
    vc
    -0.07
    CHEDULE
    -0.07
    )t
    -0.07
    _room
    -0.07
    POSITIVE LOGITS
    txt
    0.08
     bang
    0.07
     хлоп
    0.07
     '',
    0.07
     التاريخ
    0.07
     Tos
    0.07
     brutally
    0.07
     slows
    0.07
    adar
    0.07
    риот
    0.07
    Activations Density 0.002%

    No Known Activations