© 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. 19-RESID-POST-AA
    11. 22055
    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
    ங்கு
    -0.08
     Đây
    -0.08
     llegando
    -0.08
     formando
    -0.07
     decorr
    -0.07
    몸
    -0.07
     criando
    -0.07
     используя
    -0.07
     geta
    -0.07
     것이
    -0.07
    POSITIVE LOGITS
     says
    0.21
     advises
    0.19
     encourages
    0.18
     prohibits
    0.18
     suggests
    0.18
     recommends
    0.17
     പറയുന്നു
    0.16
    要求
    0.16
     говорит
    0.15
     instruct
    0.15
    Activations Density 0.013%

    No Known Activations