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. 48216
    Prev
    Next
    INDEX
    Explanations

    Geometry partitioning

    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
    ेशक
    -0.08
    ėj
    -0.08
    engl
    -0.08
     empathy
    -0.07
     shift
    -0.07
     overhaul
    -0.07
    eneric
    -0.07
     diretamente
    -0.07
    (debug
    -0.07
     หรือ
    -0.07
    POSITIVE LOGITS
     subdivisions
    0.13
    裂
    0.11
    拆
    0.11
     splitted
    0.11
     divides
    0.11
     splits
    0.11
    .Split
    0.11
     dividing
    0.11
     partitions
    0.10
     subdiv
    0.10
    Activations Density 0.028%

    No Known Activations