© 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. 980
    Prev
    Next
    INDEX
    Explanations

    impl

    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
     Fifth
    -0.08
    classmethod
    -0.08
     हुँदै
    -0.08
     भइरहेको
    -0.08
    Help
    -0.08
     NST
    -0.08
     indirectly
    -0.07
    ishi
    -0.07
     najman
    -0.07
    Indirect
    -0.07
    POSITIVE LOGITS
    简单
    0.13
     simple
    0.12
     simplistic
    0.12
     simples
    0.12
     simpl
    0.12
     eenvoudige
    0.11
    _simple
    0.11
     jednoduch
    0.11
     sederhana
    0.11
     einfachen
    0.11
    Activations Density 0.018%

    No Known Activations