© 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. 19819
    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
     સરકારે
    -0.09
     élég
    -0.09
     MERCHANTABILITY
    -0.09
    XHR
    -0.08
     elegante
    -0.08
    šlo
    -0.08
    icers
    -0.08
     refunded
    -0.08
     PRIVATE
    -0.08
    _minus
    -0.08
    POSITIVE LOGITS
     clueless
    0.16
     lovable
    0.15
     हमेशा
    0.14
     antics
    0.14
    always
    0.14
     simplistic
    0.13
     misguided
    0.13
     constamment
    0.13
     always
    0.13
     incess
    0.13
    Activations Density 0.034%

    No Known Activations