© 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. 18426
    Prev
    Next
    INDEX
    Explanations

    dissolving

    np_max-act-logits · gemini-2.0-flash
    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
     nomination
    -0.10
     corridor
    -0.09
     poster
    -0.09
     clique
    -0.08
     Corridor
    -0.08
     محافظ
    -0.08
     thrott
    -0.08
     theaters
    -0.08
     chronology
    -0.08
     ηλικ
    -0.08
    POSITIVE LOGITS
     dissolution
    0.30
     dissolve
    0.29
     dissolved
    0.29
     dissol
    0.29
     раствор
    0.24
     Diss
    0.23
     oplossen
    0.22
     opgelost
    0.22
     দ্র
    0.18
     lossen
    0.18
    Activations Density 0.017%

    No Known Activations