© 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. 51499
    Prev
    Next
    INDEX
    Explanations

    incom

    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
    通常
    -0.09
    可以
    -0.09
     peux
    -0.08
    亦
    -0.08
     можем
    -0.08
     elegant
    -0.07
    irable
    -0.07
    iriye
    -0.07
    yny
    -0.07
     įvair
    -0.07
    POSITIVE LOGITS
    pleto
    0.10
     התא
    0.08
    pleta
    0.08
    aban
    0.08
    ODA
    0.07
     pilot
    0.07
     Voll
    0.07
    plets
    0.07
    tay
    0.07
     Door
    0.07
    Activations Density 0.000%

    No Known Activations