© 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. 19783
    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
     diverses
    -0.10
     diversos
    -0.09
     diversidad
    -0.08
     berbagai
    -0.08
     flexibil
    -0.08
     विविध
    -0.08
     various
    -0.08
     burge
    -0.08
     വിവിധ
    -0.08
     Halle
    -0.08
    POSITIVE LOGITS
    ตรวจ
    0.09
     настолько
    0.09
     검
    0.09
     ίδιο
    0.08
    Checking
    0.08
    _STATE
    0.08
     상태
    0.08
    ecção
    0.08
    _state
    0.08
     되고
    0.08
    Activations Density 0.000%

    No Known Activations