© 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. 20217
    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
    —we
    -0.09
     ја
    -0.09
    thinking
    -0.08
     hassle
    -0.08
    think
    -0.08
     அல்லது
    -0.08
    —you
    -0.08
     speeding
    -0.07
     fikir
    -0.07
    —I
    -0.07
    POSITIVE LOGITS
     اولیه
    0.08
    _that
    0.08
    ieder
    0.08
     that
    0.08
     insgesamt
    0.08
    再次
    0.08
     STDMETHODCALLTYPE
    0.08
    र्तमान
    0.08
    ificaciones
    0.08
    ിയ
    0.08
    Activations Density 0.000%

    No Known Activations