© 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. 21320
    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
    numerusform
    -0.09
     naats
    -0.09
    سانة
    -0.08
    لفات
    -0.08
    FORMA
    -0.07
    Reblog
    -0.07
    rà
    -0.07
    shada
    -0.07
     uporablja
    -0.07
     ن
    -0.07
    POSITIVE LOGITS
     części
    0.10
     algún
    0.09
     meie
    0.09
     між
    0.08
     काही
    0.08
     sommige
    0.08
    ΟΣ
    0.08
     někter
    0.08
     XY
    0.08
     કેટલાક
    0.08
    Activations Density 0.107%

    No Known Activations