© 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. 51794
    Prev
    Next
    INDEX
    Explanations

    од

    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
     जिन्होंने
    -0.08
     gegeben
    -0.08
    zeit
    -0.08
    KY
    -0.08
     čas
    -0.07
     skład
    -0.07
    umfang
    -0.07
     kyn
    -0.07
    gegen
    -0.07
    .day
    -0.07
    POSITIVE LOGITS
    ност
    0.10
    ि�
    0.08
    ्शन
    0.08
    н
    0.08
    ્ર
    0.08
    ્રી
    0.08
    _Order
    0.08
    գ
    0.08
    WORD
    0.08
    િ
    0.07
    Activations Density 0.001%

    No Known Activations