© 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. 21811
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     hizmet
    -0.08
     sitesi
    -0.08
     sonuç
    -0.08
    같
    -0.08
    服務
    -0.08
    必中
    -0.07
     cafes
    -0.07
    六
    -0.07
     recepción
    -0.07
    部分
    -0.07
    POSITIVE LOGITS
     profiel
    0.11
    "profile
    0.11
     профиль
    0.11
     profile
    0.11
    profile
    0.10
    _PROFILE
    0.10
    _profile
    0.10
    Profile
    0.10
    .Profile
    0.10
     perfil
    0.10
    Activations Density 0.001%

    No Known Activations