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. 54124
    Prev
    Next
    INDEX
    Explanations

    prosecutor

    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
     mott
    -0.09
     respondeu
    -0.08
     الإج
    -0.08
    .resize
    -0.08
     salon
    -0.08
     cushions
    -0.08
    鞋
    -0.08
     chaussures
    -0.08
     aktiviert
    -0.08
     cushioning
    -0.08
    POSITIVE LOGITS
     prosecut
    0.15
     prosecutors
    0.15
     prosec
    0.13
     Prosecut
    0.13
     prosecutor
    0.13
     prosecution
    0.13
     prosecute
    0.13
     अभिय
    0.11
     Fiscalía
    0.10
     prosecuted
    0.10
    Activations Density 0.051%

    No Known Activations