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. 90990
    Prev
    Next
    INDEX
    Explanations

    –

    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
     remark
    -0.08
     Suddenly
    -0.08
    eltje
    -0.08
     ๆ
    -0.08
     Undert
    -0.08
     Kos
    -0.08
     kasus
    -0.08
    -0.08
     saat
    -0.07
     Oleh
    -0.07
    POSITIVE LOGITS
    .proto
    0.08
     Bulls
    0.08
     decisive
    0.08
     পরিচ
    0.07
     establish
    0.07
    IFEST
    0.07
     व्यापक
    0.07
     García
    0.07
     Bla
    0.07
     definitive
    0.07
    Activations Density 0.016%

    No Known Activations