© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 50137
    Prev
    Next
    INDEX
    Explanations

    say ego

    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
     вместе
    -0.08
     conjuntamente
    -0.08
    Together
    -0.08
     juntos
    -0.08
     zajedno
    -0.08
    Batis
    -0.07
     tillsammans
    -0.07
     skupaj
    -0.07
    _tbl
    -0.07
     together
    -0.07
    POSITIVE LOGITS
    ego
    0.13
     scap
    0.10
    hela
    0.09
    gevo
    0.08
    ifico
    0.08
    acea
    0.08
    agus
    0.08
    helm
    0.08
    adır
    0.08
    ula
    0.08
    Activations Density 0.001%

    No Known Activations