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. 113887
    Prev
    Next
    INDEX
    Explanations

    cellular automata

    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
     remuneration
    -0.11
     machining
    -0.09
     salario
    -0.09
     financing
    -0.09
     (€
    -0.08
     mileage
    -0.08
     earnings
    -0.08
    irp
    -0.08
     waived
    -0.08
    Mileage
    -0.08
    POSITIVE LOGITS
    _neighbors
    0.12
    _neighbor
    0.12
    Neighbor
    0.12
     Conway
    0.11
     Neighbor
    0.11
     neighbors
    0.11
    Neighbour
    0.11
    Neighbors
    0.11
     neighboring
    0.11
    Neighborhood
    0.10
    Activations Density 0.016%

    No Known Activations