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. 60308
    Prev
    Next
    INDEX
    Explanations

    eutrophication and nutrients

    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
     horseback
    -0.08
     disple
    -0.08
     effectieve
    -0.08
     Invisalign
    -0.08
     insanity
    -0.08
     COP
    -0.08
     probate
    -0.08
     irrational
    -0.08
     orthopedic
    -0.08
    ETO
    -0.08
    POSITIVE LOGITS
     Amp
    0.08
     nutrients
    0.08
     pathways
    0.08
     nutrient
    0.07
     katal
    0.07
    -------------
    0.07
     sun
    0.07
     fertil
    0.07
     javax
    0.07
    kv
    0.07
    Activations Density 0.001%

    No Known Activations