© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 97658
    Prev
    Next
    INDEX
    Explanations

    guidance/instructions

    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
     derivatives
    -0.08
    atrices
    -0.08
    ází
    -0.07
    马
    -0.07
     pits
    -0.07
     blinking
    -0.07
     occurs
    -0.07
    hic
    -0.07
     العق
    -0.07
     fallo
    -0.07
    POSITIVE LOGITS
    pare
    0.08
    ïnv
    0.08
    uwd
    0.08
    ૂ
    0.08
     Factor
    0.08
    iteerd
    0.08
    probeerd
    0.08
     Feel
    0.08
     Rochelle
    0.07
    elings
    0.07
    Activations Density 0.000%

    No Known Activations