© 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. 19-RESID-POST-AA
    11. 20491
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _->
    -0.08
     없는
    -0.07
     tận
    -0.07
     can
    -0.07
    _Status
    -0.07
     sangat
    -0.07
    played
    -0.07
    zana
    -0.07
     있는
    -0.07
     pares
    -0.07
    POSITIVE LOGITS
     necessary
    0.24
    necessary
    0.21
    必要
    0.20
     sufficient
    0.19
     જરૂરી
    0.19
    Necessary
    0.19
     necessário
    0.19
     necesario
    0.19
     необходимых
    0.18
     necesaria
    0.18
    Activations Density 0.009%

    No Known Activations