© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 64717
    Prev
    Next
    INDEX
    Explanations

    relative position

    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
    abcd
    -0.08
    気
    -0.08
     amacı
    -0.08
    ನ್ನ
    -0.08
     �
    -0.08
     dostęp
    -0.07
     tổ
    -0.07
     אב
    -0.07
     eleg
    -0.07
     Türkiye
    -0.07
    POSITIVE LOGITS
     nhau
    0.10
    quel
    0.09
    ilhar
    0.09
     kanan
    0.08
     correspondente
    0.08
     sams
    0.07
     oth
    0.07
     stronger
    0.07
     Strong
    0.07
     izquierdo
    0.07
    Activations Density 0.016%

    No Known Activations