© 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. 51214
    Prev
    Next
    INDEX
    Explanations

    ди

    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
    ేశ
    -0.08
     provoke
    -0.07
    -0.07
    iciência
    -0.07
    loč
    -0.07
    �
    -0.07
    abetes
    -0.07
    rological
    -0.07
    -0.07
     anore
    -0.07
    POSITIVE LOGITS
    аметр
    0.10
    qqat
    0.10
    дау
    0.10
    фф
    0.09
    кую
    0.09
    ареи
    0.08
    эл
    0.08
    ҳам
    0.08
    ensen
    0.08
    да
    0.08
    Activations Density 0.002%
    No Known Activations