© 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. 21753
    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
    ાજેત
    -0.10
     suspects
    -0.09
    ុល
    -0.08
     жара
    -0.08
     rainfall
    -0.08
    itab
    -0.08
     ดาวน์โหลด
    -0.08
    ��
    -0.08
     glance
    -0.08
     વરસાદ
    -0.08
    POSITIVE LOGITS
     branding
    0.27
     Branding
    0.25
     positioning
    0.25
    定位
    0.22
     differentiation
    0.22
     пози
    0.20
    branding
    0.20
     Position
    0.20
     posicion
    0.20
     differentiate
    0.19
    Activations Density 0.057%

    No Known Activations