© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 5394
    Prev
    Next
    INDEX
    Explanations

    substitution

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disputed
    -0.08
    怎么算
    -0.07
    abilang
    -0.07
     afgesloten
    -0.07
     Folder
    -0.07
     akkurat
    -0.07
     Popup
    -0.07
     müssen
    -0.07
     elementum
    -0.07
     конкрет
    -0.07
    POSITIVE LOGITS
     substitution
    0.34
     substitutions
    0.29
     substitute
    0.28
     substit
    0.27
     Substitute
    0.25
     परिवर्तन
    0.24
     change
    0.24
     sustit
    0.23
     transformation
    0.23
    変
    0.23
    Activations Density 0.227%

    No Known Activations