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. 56179
    Prev
    Next
    INDEX
    Explanations

    fixture/fan

    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
     franca
    -0.08
    akka
    -0.08
    ayaan
    -0.08
    ತ್ಸ
    -0.08
     estrategia
    -0.08
     پول
    -0.08
    atoria
    -0.08
    ')],↵
    -0.08
     }()↵
    -0.08
    "ב
    -0.08
    POSITIVE LOGITS
     replacement
    0.09
     स्थापित
    0.09
     फिट
    0.09
     Replacement
    0.08
    .onload
    0.08
     Fitbit
    0.08
     installed
    0.08
    安装
    0.08
     remplacement
    0.08
     raccord
    0.08
    Activations Density 0.020%

    No Known Activations