© 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. 11-RESID-POST-AA
    11. 63308
    Prev
    Next
    INDEX
    Explanations

    probability

    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
     సందర్భంగా
    -0.08
     puff
    -0.08
     accommod
    -0.08
     వేస
    -0.08
     �
    -0.08
     モ
    -0.08
     ビ
    -0.08
     ABD
    -0.08
    еси
    -0.08
     చోట
    -0.08
    POSITIVE LOGITS
     probabilities
    0.11
     probability
    0.09
     predictions
    0.09
     quantum
    0.09
     probabil
    0.09
     squared
    0.09
    _prob
    0.08
    最多
    0.08
     predicts
    0.08
    Probability
    0.08
    Activations Density 0.003%

    No Known Activations