© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16656
    Prev
    Next
    INDEX
    Explanations

    protecting

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     inscrit
    -0.08
     certificado
    -0.08
     agregado
    -0.08
    WG
    -0.08
    (Base
    -0.08
    еме
    -0.08
    Membership
    -0.08
    Embed
    -0.07
     iscr
    -0.07
     pride
    -0.07
    POSITIVE LOGITS
     protecting
    0.14
     protects
    0.14
     Protect
    0.14
     protéger
    0.13
     protections
    0.13
     beschermen
    0.12
     schützt
    0.12
    Protect
    0.12
     보호
    0.12
     protective
    0.12
    Activations Density 0.006%

    No Known Activations