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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 43811
    Prev
    Next
    INDEX
    Explanations

    job applications

    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
     deco
    -0.08
    baby
    -0.08
    fond
    -0.08
    .Pending
    -0.08
    †
    -0.07
     foundation
    -0.07
     accom
    -0.07
     Essay
    -0.07
     foundational
    -0.07
    it
    -0.07
    POSITIVE LOGITS
    渠道
    0.16
     канал
    0.11
    途
    0.11
     canais
    0.10
     وسائل
    0.10
     canales
    0.10
     vía
    0.10
     арқылы
    0.10
     социальной
    0.09
     channels
    0.09
    Activations Density 0.052%

    No Known Activations