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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130998
    Prev
    Next
    INDEX
    Explanations

    alloys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toilet
    -0.12
     туал
    -0.10
     Toilet
    -0.09
     bathrooms
    -0.09
     toilets
    -0.09
     Wrapped
    -0.09
     selfies
    -0.08
     banheiro
    -0.08
     Funnel
    -0.08
    厕所
    -0.08
    POSITIVE LOGITS
     alloys
    0.33
     alloy
    0.32
     Alloy
    0.25
     steels
    0.21
     metallurgy
    0.20
     metall
    0.16
     aliaj
    0.16
     Austen
    0.16
     alli
    0.16
     carbur
    0.15
    Activations Density 0.035%

    No Known Activations