© 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. 18757
    Prev
    Next
    INDEX
    Explanations

    fait

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     силь
    -0.09
     ?>">
↵
    -0.08
    ответ
    -0.08
     ответ
    -0.08
    onday
    -0.08
     ац
    -0.08
    神马
    -0.08
     ар
    -0.08
    cres
    -0.08
    ASIC
    -0.08
    POSITIVE LOGITS
    न्होंने
    0.08
     necessariamente
    0.08
     principes
    0.08
    .jsdelivr
    0.08
     Winners
    0.08
    ्घ
    0.08
     bovendien
    0.07
    apeake
    0.07
    wenen
    0.07
    میل
    0.07
    Activations Density 0.000%

    No Known Activations