© 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. 51386
    Prev
    Next
    INDEX
    Explanations

    T

    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
    argin
    -0.08
     Regel
    -0.08
    reg
    -0.08
    pants
    -0.08
     말했다
    -0.08
    arg
    -0.07
    registrement
    -0.07
    eted
    -0.07
     развит
    -0.07
    (arg
    -0.07
    POSITIVE LOGITS
     ações
    0.09
     ação
    0.08
     tüket
    0.08
     tradicionais
    0.08
     pemain
    0.08
     humanas
    0.08
     oyunc
    0.08
     consum
    0.08
     actions
    0.08
    anee
    0.08
    Activations Density 0.000%

    No Known Activations