© 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 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. 64025
    Prev
    Next
    INDEX
    Explanations

    contest

    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
    Ä
    -0.09
    HER
    -0.09
    porte
    -0.08
    �
    -0.08
     teo
    -0.08
    º
    -0.08
    träge
    -0.08
     tiltak
    -0.07
     режим
    -0.07
     Θ
    -0.07
    POSITIVE LOGITS
     ensin
    0.09
     हमेशा
    0.08
     Manuals
    0.08
     Straw
    0.08
     Something
    0.08
     estaduais
    0.08
     právě
    0.08
     ruang
    0.08
     fascination
    0.08
     davvero
    0.08
    Activations Density 0.017%

    No Known Activations