© 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. 19-RESID-POST-AA
    11. 103462
    Prev
    Next
    INDEX
    Explanations

    add

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lovable
    -0.09
     popularity
    -0.08
     openness
    -0.07
     showcasing
    -0.07
     flashy
    -0.07
     beautifully
    -0.07
     links
    -0.07
     rankings
    -0.07
     stumble
    -0.07
     showcased
    -0.07
    POSITIVE LOGITS
     additives
    0.17
     əlavə
    0.16
    添加
    0.16
     添加
    0.16
     ajouté
    0.16
     Добав
    0.15
     добавить
    0.14
     ઉમ
    0.14
     добав
    0.14
     añadido
    0.14
    Activations Density 0.009%

    No Known Activations