© 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. 103504
    Prev
    Next
    INDEX
    Explanations

    size dimensions

    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
    אַק
    -0.09
    atisation
    -0.09
    /set
    -0.09
    ിരിക്കുന്നത്
    -0.08
     Offices
    -0.08
    /domain
    -0.08
     Él
    -0.08
    /ac
    -0.08
    ुभ
    -0.08
     органов
    -0.08
    POSITIVE LOGITS
    Interest
    0.08
     aplica
    0.07
     sleek
    0.07
    .fn
    0.07
    <meta
    0.07
    ds
    0.07
    enet
    0.07
     stylish
    0.07
    Fornecedor
    0.07
    Def
    0.07
    Activations Density 0.001%

    No Known Activations