© 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. 22194
    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
     alias
    -0.09
    ிஷ
    -0.08
     submission
    -0.08
    submission
    -0.08
    INGTON
    -0.08
     workload
    -0.08
     staging
    -0.08
    SECONDS
    -0.07
     resets
    -0.07
    _ENDIAN
    -0.07
    POSITIVE LOGITS
     wonderful
    0.10
     духов
    0.09
     mogelijkheden
    0.09
     করোন
    0.09
     обычно
    0.09
     انواع
    0.09
    жди
    0.09
     бик
    0.09
     yleensä
    0.09
    usually
    0.09
    Activations Density 0.004%

    No Known Activations