© 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. 70353
    Prev
    Next
    INDEX
    Explanations

    in

    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
    .pass
    -0.08
    inais
    -0.07
    ulugan
    -0.07
     તેવી
    -0.07
     determine
    -0.07
     moindre
    -0.07
    .observe
    -0.07
    _ACCEPT
    -0.07
    chin
    -0.07
     personnelles
    -0.07
    POSITIVE LOGITS
     abad
    0.08
     Dmit
    0.08
     Dik
    0.08
    0.08
     skozi
    0.08
     Orc
    0.08
     bie
    0.07
     sisse
    0.07
    besch
    0.07
    }$/
    0.07
    Activations Density 0.004%
    No Known Activations