© 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. 11-RESID-POST-AA
    11. 70639
    Prev
    Next
    INDEX
    Explanations

    hetic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zwa
    -0.08
    elkast
    -0.08
     competitie
    -0.08
    Celebrate
    -0.08
    edict
    -0.07
     promulg
    -0.07
    EDI
    -0.07
    edi
    -0.07
    Mapa
    -0.07
     ID
    -0.07
    POSITIVE LOGITS
    ể
    0.07
     κα
    0.07
     llam
    0.07
     analogue
    0.07
    當
    0.07
     minis
    0.07
    ат
    0.07
     upang
    0.07
     Hughes
    0.07
     Då
    0.07
    Activations Density 0.000%

    No Known Activations