© 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. 69991
    Prev
    Next
    INDEX
    Explanations

    comic

    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
     vermeiden
    -0.08
     více
    -0.08
    」に
    -0.08
    391
    -0.07
    ditions
    -0.07
    vada
    -0.07
    」を
    -0.07
    mán
    -0.07
     содерж
    -0.07
    열
    -0.07
    POSITIVE LOGITS
     Collar
    0.08
     Turkey
    0.08
     Terry
    0.08
    拜
    0.08
     kaas
    0.08
     Luigi
    0.08
    0.08
     Benedict
    0.07
     Kais
    0.07
     towel
    0.07
    Activations Density 0.000%
    No Known Activations