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. 106048
    Prev
    Next
    INDEX
    Explanations

    polynomial arithmetic

    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
     beruf
    -0.08
    Accessible
    -0.08
     firefighters
    -0.08
     industri
    -0.08
     geopolitical
    -0.08
     Accessible
    -0.07
    .offset
    -0.07
     brood
    -0.07
     comb
    -0.07
    涙
    -0.07
    POSITIVE LOGITS
     นี้
    0.08
    .Invalid
    0.08
    音
    0.08
     invalid
    0.08
     remover
    0.08
     eliminar
    0.07
     Dz
    0.07
    _audio
    0.07
    Clause
    0.07
     abol
    0.07
    Activations Density 0.006%

    No Known Activations