© 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. 23-RESID-POST-AA
    11. 50779
    Prev
    Next
    INDEX
    Explanations

    always

    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
     ofta
    -0.16
     souvent
    -0.16
     Often
    -0.15
     geralmente
    -0.15
     často
    -0.15
     često
    -0.15
     toujours
    -0.15
     often
    -0.15
    通常
    -0.15
     ofte
    -0.15
    POSITIVE LOGITS
     behalve
    0.12
    -таки
    0.12
     voorkomende
    0.12
     रहेगा
    0.12
    -present
    0.12
     been
    0.12
    cky
    0.12
     haverá
    0.11
     izango
    0.11
    -on
    0.11
    Activations Density 0.029%

    No Known Activations