© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 97541
    Prev
    Next
    INDEX
    Explanations

    кар

    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
    13
    -0.09
     teamwork
    -0.08
     confr
    -0.08
    １２
    -0.08
    23
    -0.08
     prévention
    -0.08
    400
    -0.08
    Lm
    -0.08
    500
    -0.08
    126
    -0.08
    POSITIVE LOGITS
    ета
    0.08
    ету
    0.08
    ్ట్ర
    0.08
    riages
    0.08
     segmentos
    0.08
     груз
    0.08
    tridge
    0.07
    шер
    0.07
    ritos
    0.07
     duck
    0.07
    Activations Density 0.003%

    No Known Activations