Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 108819
    Prev
    Next
    INDEX
    Explanations

    harvesting

    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
     Sandbox
    -0.08
    Sandbox
    -0.08
    Loads
    -0.08
    Exists
    -0.08
    Hosting
    -0.07
    Yn
    -0.07
    Driven
    -0.07
    Wel
    -0.07
     поис
    -0.07
    Heating
    -0.07
    POSITIVE LOGITS
     harvesting
    0.13
     harvested
    0.13
     урож
    0.12
     Harvest
    0.11
     harvest
    0.11
    剪
    0.11
     Extraction
    0.10
    摘
    0.10
     pumpkins
    0.09
     cuidadosamente
    0.09
    Activations Density 0.023%

    No Known Activations