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. 54403
    Prev
    Next
    INDEX
    Explanations

    turkey

    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
     equipos
    -0.08
    tanggal
    -0.07
     herramientas
    -0.07
     قرارداد
    -0.07
     deis
    -0.07
     تقسیم
    -0.07
     קור
    -0.07
     setups
    -0.07
     escalating
    -0.07
     Nodes
    -0.07
    POSITIVE LOGITS
    736
    0.08
     Soldier
    0.08
    Cors
    0.08
    /home
    0.08
     Walnut
    0.08
    _ml
    0.08
    Homepage
    0.07
     Mord
    0.07
    _OB
    0.07
     cran
    0.07
    Activations Density 0.003%

    No Known Activations