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. 88231
    Prev
    Next
    INDEX
    Explanations

    la

    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
    resents
    -0.08
    -readable
    -0.08
    cher
    -0.08
    gült
    -0.07
    ifies
    -0.07
     целей
    -0.07
    ograms
    -0.07
    िकल
    -0.07
    (Of
    -0.07
    uable
    -0.07
    POSITIVE LOGITS
     GMC
    0.09
     manor
    0.08
     Violence
    0.08
     countryside
    0.08
     Hen
    0.08
     violence
    0.08
     Vie
    0.08
     Sociale
    0.07
     neck
    0.07
     ”
    0.07
    Activations Density 0.010%

    No Known Activations