© 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. 111397
    Prev
    Next
    INDEX
    Explanations

    :

    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
     tomorrow
    -0.10
    verbs
    -0.09
     ambientais
    -0.09
     getenv
    -0.09
     ambientales
    -0.08
     تعیین
    -0.08
     Appetite
    -0.08
     persuasion
    -0.08
     sebesar
    -0.08
     journalism
    -0.08
    POSITIVE LOGITS
     arrangement
    0.12
     rectangular
    0.11
     symmetrical
    0.10
     iconic
    0.10
     alternating
    0.09
    排列
    0.09
     arrangements
    0.09
     adjacency
    0.09
    -shaped
    0.09
     schematic
    0.09
    Activations Density 0.047%

    No Known Activations