© 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. 29135
    Prev
    Next
    INDEX
    Explanations

    telescopes

    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
     mayonnaise
    -0.10
    ptype
    -0.08
    _children
    -0.08
     struktur
    -0.08
    .dumps
    -0.08
     plastique
    -0.08
    般
    -0.08
    clipboard
    -0.08
    ographies
    -0.08
    _far
    -0.07
    POSITIVE LOGITS
     rooftop
    0.11
     telesc
    0.09
     astronom
    0.09
     Observatory
    0.09
     MAGIC
    0.09
     ముందు
    0.08
     dome
    0.08
     wavelengths
    0.08
     시설
    0.08
    397
    0.08
    Activations Density 0.005%

    No Known Activations