© 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. 30301
    Prev
    Next
    INDEX
    Explanations

    esta

    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
    :G
    -0.08
    -sch
    -0.08
    :g
    -0.07
    ,min
    -0.07
    -cycle
    -0.07
    ,G
    -0.07
    इस
    -0.07
    gaan
    -0.07
    _notice
    -0.07
     उनकी
    -0.07
    POSITIVE LOGITS
     complementary
    0.09
     complement
    0.09
     iink
    0.09
    ↵//
    0.09
    Complement
    0.08
     counterparts
    0.08
     complémentaires
    0.08
     ظل
    0.08
     zomwe
    0.08
     complément
    0.08
    Activations Density 0.446%

    No Known Activations