© 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. 103621
    Prev
    Next
    INDEX
    Explanations

    say "why"

    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
    _mobile
    -0.09
    _packet
    -0.09
    ಟ್ಟ
    -0.09
    _map
    -0.09
     Fläche
    -0.08
    _stock
    -0.08
    _asset
    -0.08
     móvel
    -0.08
    tabl
    -0.08
    _updates
    -0.08
    POSITIVE LOGITS
     dahilan
    0.17
     razloga
    0.17
     أسباب
    0.16
     sababu
    0.16
     redenen
    0.15
     لماذا
    0.15
    原因
    0.15
     причинам
    0.15
     razlog
    0.15
     الأسباب
    0.15
    Activations Density 0.015%

    No Known Activations