© 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 EvalsExportsinterp-engineNEWAPI 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. 19127
    Prev
    Next
    INDEX
    Explanations

    现代

    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
     designers
    -0.10
    iminate
    -0.09
    -designed
    -0.08
    orical
    -0.08
     designs
    -0.08
    perator
    -0.08
     interpretar
    -0.08
    istically
    -0.08
     wording
    -0.08
    istic
    -0.08
    POSITIVE LOGITS
    화를
    0.11
     الغربية
    0.10
    ায়
    0.09
    итаи
    0.09
     북한
    0.09
     dönüş
    0.09
     രാഷ്ട
    0.09
     государственной
    0.09
     vallée
    0.09
    Initialization
    0.09
    Activations Density 0.004%

    No Known Activations