© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64029
    Prev
    Next
    INDEX
    Explanations

    empty stomach workout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     influência
    -0.08
     influencia
    -0.08
     influence
    -0.08
     suka
    -0.08
     Einfluss
    -0.08
     минист
    -0.08
     влияние
    -0.08
     Муж
    -0.07
     सामने
    -0.07
     xmin
    -0.07
    POSITIVE LOGITS
    -most
    0.08
    azón
    0.08
    845
    0.08
    most
    0.07
    lyn
    0.07
    lyg
    0.07
    dd
    0.07
    'autre
    0.07
    overn
    0.07
     mehreren
    0.07
    Activations Density 0.010%

    No Known Activations