© 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. 23-RESID-POST-AA
    11. 6551
    Prev
    Next
    INDEX
    Explanations

    ability

    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
     человеком
    -0.08
     histogram
    -0.08
    同比
    -0.07
    וני
    -0.07
    -carousel
    -0.07
     convencional
    -0.07
     രേഖ
    -0.07
    .Strict
    -0.07
     člov
    -0.07
     базы
    -0.07
    POSITIVE LOGITS
     ability
    0.26
     Fähigkeit
    0.23
    Ability
    0.23
     Ability
    0.23
     abilities
    0.22
     способность
    0.21
    能力
    0.21
     habilidade
    0.20
     habilidad
    0.20
    技能
    0.19
    Activations Density 0.063%

    No Known Activations