© 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. 5454
    Prev
    Next
    INDEX
    Explanations

    рос

    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
     бағдарлам
    -0.08
     Telecom
    -0.08
     humidity
    -0.08
     kiri
    -0.08
     decorrer
    -0.07
     պատկեր
    -0.07
    -day
    -0.07
    umps
    -0.07
     έ
    -0.07
    ivt
    -0.07
    POSITIVE LOGITS
     roz
    0.10
    .skip
    0.09
    versorgung
    0.08
    _stop
    0.08
    .stop
    0.08
    install
    0.08
    .Install
    0.08
    _skip
    0.08
    kosten
    0.08
    рощ
    0.08
    Activations Density 0.001%

    No Known Activations