© 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. 19-RESID-POST-AA
    11. 102280
    Prev
    Next
    INDEX
    Explanations

    Data processing

    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
     նման
    -0.09
     გამოს
    -0.08
     gerekli
    -0.08
    彩票网
    -0.08
     huko
    -0.08
     nyingi
    -0.08
     phakathi
    -0.08
     stichting
    -0.08
     აუცილ
    -0.08
    彩票官网
    -0.08
    POSITIVE LOGITS
     afterward
    0.08
    вед
    0.08
    dm
    0.08
     encouragement
    0.07
    ingt
    0.07
    encing
    0.07
     afterwards
    0.07
    ancang
    0.07
    DH
    0.07
     послед
    0.07
    Activations Density 0.000%

    No Known Activations