© 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. 11-RESID-POST-AA
    11. 75729
    Prev
    Next
    INDEX
    Explanations

    ranking evaluation metrics

    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
    abino
    -0.08
     correlations
    -0.08
     staining
    -0.08
    oriasis
    -0.07
    猜
    -0.07
    ajari
    -0.07
     শুক
    -0.07
    auw
    -0.07
    ưa
    -0.07
     penyakit
    -0.07
    POSITIVE LOGITS
    Bent
    0.10
     obedience
    0.09
     predecessor
    0.08
     plato
    0.08
     marcher
    0.07
     Ursula
    0.07
    hare
    0.07
     pled
    0.07
    Impro
    0.07
    Moderator
    0.07
    Activations Density 0.000%

    No Known Activations