© 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. 51730
    Prev
    Next
    INDEX
    Explanations

    Non-english text

    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
    -key
    -0.08
    -param
    -0.08
     Mat
    -0.08
    _PARAM
    -0.08
    حب
    -0.08
    ুট
    -0.07
    -lasting
    -0.07
    over
    -0.07
    uth
    -0.07
    cases
    -0.07
    POSITIVE LOGITS
    hluk
    0.09
     ఎ
    0.08
     मूल्य
    0.08
     valores
    0.08
    价值
    0.08
    aming
    0.08
     catastrophic
    0.07
    ुरी
    0.07
     værd
    0.07
    價
    0.07
    Activations Density 0.000%

    No Known Activations