© 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. 23-RESID-POST-AA
    11. 51788
    Prev
    Next
    INDEX
    Explanations

    Technical, mixed language

    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
    este
    -0.08
    .trans
    -0.07
    roup
    -0.07
    trans
    -0.07
    	trans
    -0.07
     Με
    -0.07
     cupid
    -0.07
     Cupid
    -0.07
    moid
    -0.07
     breed
    -0.07
    POSITIVE LOGITS
    ям
    0.11
    انع
    0.09
    ایه
    0.09
    הליך
    0.09
    амъ
    0.09
    ями
    0.08
     qued
    0.08
    اني
    0.08
    انی
    0.08
     leggen
    0.08
    Activations Density 0.001%

    No Known Activations