© 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. 18861
    Prev
    Next
    INDEX
    Explanations

    redemption and salvation

    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
    投诉
    -0.09
     BSON
    -0.08
     حرف
    -0.08
     complaints
    -0.08
    ihini
    -0.08
    رافق
    -0.08
     picky
    -0.08
     Tehran
    -0.08
     verschw
    -0.08
     MATLAB
    -0.08
    POSITIVE LOGITS
     redemption
    0.24
     salvation
    0.24
     Redemption
    0.20
    救
    0.19
     redeem
    0.18
     redeemed
    0.17
     спас
    0.17
     reden
    0.16
    救世
    0.15
     grace
    0.15
    Activations Density 0.030%

    No Known Activations