© 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 EvalsExportsinterp-engineNEWAPI 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. 21999
    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
     հավատ
    -0.08
    каж
    -0.08
    issaat
    -0.08
    yayari
    -0.08
    ==↵
    -0.08
    <-
    -0.08
     վստահ
    -0.08
     וויסן
    -0.08
     Худ
    -0.08
     азыр
    -0.08
    POSITIVE LOGITS
     complement
    0.52
     complementary
    0.52
    Complement
    0.51
     complements
    0.50
     Complement
    0.50
     ergän
    0.49
     complément
    0.49
     complementar
    0.48
     complemento
    0.47
     complémentaires
    0.47
    Activations Density 0.064%

    No Known Activations