© 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. 21360
    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
    asẹ
    -0.10
     Asking
    -0.09
     diciendo
    -0.09
    cluding
    -0.09
     qiladi
    -0.09
     이를
    -0.09
     Saying
    -0.09
     етеді
    -0.09
     قریب
    -0.09
    ируют
    -0.09
    POSITIVE LOGITS
     created
    0.28
     generated
    0.27
     produced
    0.26
     obtained
    0.25
     constructed
    0.23
     issued
    0.22
    created
    0.21
     released
    0.20
     formed
    0.20
     developed
    0.20
    Activations Density 0.087%

    No Known Activations