© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 51975
    Prev
    Next
    INDEX
    Explanations

    vag

    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
    构
    -0.07
    ुस
    -0.07
    -mod
    -0.07
    ाड
    -0.07
    -qu
    -0.07
    ]-
    -0.07
    ]]
    -0.07
    �
    -0.07
    접
    -0.07
    ]]↵↵
    -0.07
    POSITIVE LOGITS
    blr
    0.09
     العامة
    0.08
     bali
    0.08
     conto
    0.08
     gau
    0.08
     ghj
    0.08
    国内
    0.08
     hé
    0.08
     الداخلية
    0.08
     اللازمة
    0.08
    Activations Density 0.000%

    No Known Activations