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. 43425
    Prev
    Next
    INDEX
    Explanations

    Game development/scripting

    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
    了解
    -0.08
    全球
    -0.08
     congen
    -0.07
    人生
    -0.07
     tribut
    -0.07
    문
    -0.07
     ndị
    -0.07
     stringent
    -0.07
     eclectic
    -0.07
     Euros
    -0.07
    POSITIVE LOGITS
    Weapon
    0.13
    _weapon
    0.11
     melee
    0.10
     Weapon
    0.10
     mechanic
    0.10
    weapon
    0.10
     Assault
    0.10
     instantaneous
    0.10
    .weapon
    0.10
     weapon
    0.10
    Activations Density 0.005%

    No Known Activations