© 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. 51454
    Prev
    Next
    INDEX
    Explanations

    reco

    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
     Überg
    -0.08
    ==='
    -0.08
    oxe
    -0.08
     지난해
    -0.08
    oxa
    -0.08
    pub
    -0.07
    	ROM
    -0.07
    SEO
    -0.07
    laat
    -0.07
     externas
    -0.07
    POSITIVE LOGITS
    iling
    0.10
    ILER
    0.09
    ils
    0.08
    iveness
    0.08
    inder
    0.08
    0.08
     atr
    0.08
     grader
    0.08
     desen
    0.08
    uring
    0.08
    Activations Density 0.002%
    No Known Activations