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

    Neuronpedia

    Jacobian LensNEW
    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. 20277
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Flere
    -0.09
    Pesquisa
    -0.08
     выгля
    -0.08
    categories
    -0.08
     Aspekte
    -0.08
     Dysfunction
    -0.08
    сива
    -0.08
    �ి
    -0.08
     Several
    -0.08
     Problemen
    -0.08
    POSITIVE LOGITS
     impact
    0.20
     تأثير
    0.18
     impacto
    0.17
    ’impact
    0.16
     role
    0.16
     влияние
    0.16
     influence
    0.15
     effect
    0.14
     invloed
    0.14
     profound
    0.13
    Activations Density 0.033%

    No Known Activations