© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 79086
    Prev
    Next
    INDEX
    Explanations

    service

    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
    Pass
    -0.08
    illir
    -0.08
    Automatic
    -0.08
    _PASS
    -0.08
     اُس
    -0.08
    lisle
    -0.07
     silicone
    -0.07
     Dord
    -0.07
    Dutch
    -0.07
    Kinder
    -0.07
    POSITIVE LOGITS
     declare
    0.09
     sha
    0.09
     named
    0.08
     �
    0.08
     stap
    0.08
    declare
    0.08
     declaration
    0.08
     declarations
    0.08
     declaración
    0.08
     Karen
    0.07
    Activations Density 0.003%

    No Known Activations