© 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. 11-RESID-POST-AA
    11. 70719
    Prev
    Next
    INDEX
    Explanations

    phone customization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _COORD
    -0.08
     appreh
    -0.08
    -occ
    -0.08
    ocated
    -0.08
    بع
    -0.08
    -0.08
    irtschaft
    -0.08
    secutive
    -0.07
    SERV
    -0.07
     orally
    -0.07
    POSITIVE LOGITS
     personalization
    0.14
     customization
    0.14
     customizing
    0.14
     personalize
    0.12
    Customization
    0.12
     оформления
    0.12
     customized
    0.12
     personnalisé
    0.12
    Customize
    0.12
     색
    0.12
    Activations Density 0.044%
    No Known Activations