© 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. 30351
    Prev
    Next
    INDEX
    Explanations

    Lists and numbering

    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
    ANGO
    -0.07
     создан
    -0.07
    ];//
    -0.07
    ਲ
    -0.07
     જાણી
    -0.07
     okviru
    -0.07
    _curr
    -0.07
     те
    -0.07
    ечно
    -0.07
    ولد
    -0.07
    POSITIVE LOGITS
    review
    0.08
    ugh
    0.08
     Massage
    0.07
     REVIEW
    0.07
     tou
    0.07
     �
    0.07
     Sight
    0.07
    Pear
    0.07
     Demi
    0.07
    Amy
    0.07
    Activations Density 0.034%

    No Known Activations