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. 55866
    Prev
    Next
    INDEX
    Explanations

    scientific names and strains

    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
    fulfilled
    -0.10
     booklet
    -0.10
     fullscreen
    -0.09
     medication
    -0.09
     fantasy
    -0.09
     rebate
    -0.09
     canv
    -0.09
     fá
    -0.09
    秘籍
    -0.09
     FIL
    -0.09
    POSITIVE LOGITS
     pathogenic
    0.14
     bacteria
    0.13
     strains
    0.12
    菌
    0.11
     бактер
    0.10
     spores
    0.10
     bacter
    0.10
     cultured
    0.10
     microbes
    0.09
     aerobic
    0.09
    Activations Density 0.011%

    No Known Activations