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. 65846
    Prev
    Next
    INDEX
    Explanations

    poverty

    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
     vitro
    -0.08
     feline
    -0.08
     Pepsi
    -0.07
    째
    -0.07
    orsch
    -0.07
     relações
    -0.07
     relacion
    -0.07
     relations
    -0.07
     charset
    -0.07
    .hk
    -0.07
    POSITIVE LOGITS
     गांव
    0.10
     villages
    0.09
     Menschen
    0.09
     ग्रामीण
    0.08
     لتحقيق
    0.08
    ừng
    0.08
    赶
    0.08
     vượt
    0.08
     تحقيق
    0.08
    扶贫
    0.08
    Activations Density 0.004%

    No Known Activations