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. 55865
    Prev
    Next
    INDEX
    Explanations

    Groups and affiliations

    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
    .amazon
    -0.08
     ctx
    -0.08
     સંપૂર્ણ
    -0.08
     абсолют
    -0.08
    _ctx
    -0.08
     absolute
    -0.08
     empieza
    -0.08
     laba
    -0.08
     metaf
    -0.07
    akanaka
    -0.07
    POSITIVE LOGITS
     faction
    0.14
     factions
    0.14
     dissent
    0.11
     sympath
    0.11
     ferv
    0.10
     rallied
    0.10
    -minded
    0.09
     zeal
    0.09
     যারা
    0.09
     supporters
    0.09
    Activations Density 0.044%

    No Known Activations