© 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. 113358
    Prev
    Next
    INDEX
    Explanations

    dimensional

    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
     Login
    -0.08
    .decode
    -0.08
     Versicher
    -0.08
     nond
    -0.08
     Bird
    -0.07
    효
    -0.07
     Flights
    -0.07
     כדי
    -0.07
     Fragen
    -0.07
    .question
    -0.07
    POSITIVE LOGITS
    -dimensional
    0.12
    imensional
    0.10
    .Dimension
    0.09
     dimensional
    0.09
     manif
    0.08
     manifold
    0.08
    -degree
    0.08
    ambient
    0.08
    -cultural
    0.08
     Basement
    0.08
    Activations Density 0.004%

    No Known Activations