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. 119316
    Prev
    Next
    INDEX
    Explanations

    soil amendments

    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
     pulmonary
    -0.08
     Mainland
    -0.08
    invent
    -0.08
     breaches
    -0.07
    entrant
    -0.07
    Heart
    -0.07
     breach
    -0.07
    _choices
    -0.07
     呼
    -0.07
    Consumer
    -0.07
    POSITIVE LOGITS
     fertilizer
    0.16
     fertilizers
    0.15
     compost
    0.14
     Compost
    0.12
     fertil
    0.12
     Soil
    0.11
     manure
    0.11
     soil
    0.11
     mulch
    0.10
     nawo
    0.10
    Activations Density 0.014%

    No Known Activations