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. 44069
    Prev
    Next
    INDEX
    Explanations

    Unsafe prompts

    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
    -if
    -0.08
     Concord
    -0.08
     amantes
    -0.08
     의견
    -0.08
     Bydd
    -0.07
     Sempre
    -0.07
     gwamn
    -0.07
     亿
    -0.07
     Dumnezeu
    -0.07
    .ie
    -0.07
    POSITIVE LOGITS
     BLO
    0.09
     breeds
    0.08
     algoritmo
    0.08
     modernization
    0.08
     absurdo
    0.07
     absur
    0.07
     zomb
    0.07
     washed
    0.07
    øg
    0.07
    Customization
    0.07
    Activations Density 0.000%

    No Known Activations