© 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. 111126
    Prev
    Next
    INDEX
    Explanations

    :

    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
    NJ
    -0.08
     Sah
    -0.07
     induction
    -0.07
     مف
    -0.07
     الموا
    -0.07
     wonen
    -0.07
    GK
    -0.07
    irth
    -0.07
    during
    -0.07
    eket
    -0.07
    POSITIVE LOGITS
     ratio
    0.08
    }))
    0.08
    =(
    0.08
     Antique
    0.08
     Ratio
    0.08
    ratio
    0.08
     (:
    0.07
    íamos
    0.07
    ılar
    0.07
     Rede
    0.07
    Activations Density 0.014%

    No Known Activations