© 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. 99488
    Prev
    Next
    INDEX
    Explanations

    to

    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
     cuidadosamente
    -0.08
     বুঝ
    -0.08
     vraiment
    -0.08
     cleanse
    -0.08
    へ
    -0.08
    చ్
    -0.07
    Hat
    -0.07
    League
    -0.07
    Forced
    -0.07
    dotenv
    -0.07
    POSITIVE LOGITS
     asumir
    0.09
     limitations
    0.08
     liberties
    0.08
     durchaus
    0.08
    രം
    0.08
     oversight
    0.07
     speculation
    0.07
     understatement
    0.07
     speculative
    0.07
     literal
    0.07
    Activations Density 0.035%

    No Known Activations