Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 105999
    Prev
    Next
    INDEX
    Explanations

    legend

    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
     tilgang
    -0.09
     horário
    -0.08
     तीस
    -0.07
     Madh
    -0.07
     AA
    -0.07
    .at
    -0.07
     Norm
    -0.07
    �
    -0.07
    tona
    -0.07
    ndl
    -0.07
    POSITIVE LOGITS
     lore
    0.10
    传奇
    0.10
     perpet
    0.09
     legends
    0.09
    legend
    0.09
    ous
    0.08
    意义
    0.08
     dubbed
    0.08
     tales
    0.08
    性的
    0.08
    Activations Density 0.009%

    No Known Activations