© 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. 47875
    Prev
    Next
    INDEX
    Explanations

    sum

    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
    issimo
    -0.08
    issima
    -0.08
     sobie
    -0.08
    -out
    -0.08
    _HOME
    -0.08
    cuts
    -0.08
    -none
    -0.08
    out
    -0.08
     سازی
    -0.07
    roads
    -0.07
    POSITIVE LOGITS
     consumption
    0.16
    ption
    0.16
     Consumption
    0.15
     consumed
    0.15
    _consum
    0.15
    Consumption
    0.15
     consommation
    0.14
     consumo
    0.14
     fogy
    0.14
     consum
    0.14
    Activations Density 0.024%

    No Known Activations