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. 102887
    Prev
    Next
    INDEX
    Explanations

    bootstrap

    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
    nost
    -0.08
    iché
    -0.08
     quantum
    -0.08
    Quantum
    -0.08
     Quantum
    -0.08
     counting
    -0.07
     quant
    -0.07
     traduc
    -0.07
     quantified
    -0.07
     असल्य
    -0.07
    POSITIVE LOGITS
     Theo
    0.09
     경기
    0.08
    _entities
    0.08
     Thousands
    0.08
     />";↵
    0.08
     sprawling
    0.08
    全集
    0.08
     Bele
    0.08
     �
    0.08
     Knit
    0.08
    Activations Density 0.003%

    No Known Activations