© 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. 23-RESID-POST-AA
    11. 50921
    Prev
    Next
    INDEX
    Explanations

    Avoid traps

    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
    je
    -0.08
     extrap
    -0.08
    acter
    -0.07
     menus
    -0.07
     reason
    -0.07
     sublic
    -0.07
    odynamics
    -0.07
    Je
    -0.07
    MENU
    -0.07
    wan
    -0.07
    POSITIVE LOGITS
     Allow
    0.09
    _FMT
    0.09
    ेशा
    0.08
    ушки
    0.08
     es
    0.08
     zai
    0.08
     bourgeois
    0.07
     siempre
    0.07
     &___
    0.07
    sure
    0.07
    Activations Density 0.001%

    No Known Activations