© 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. 94623
    Prev
    Next
    INDEX
    Explanations

    Links/finding information

    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
     trucs
    -0.08
    ))-
    -0.07
     વાય
    -0.07
     نظام
    -0.07
    )&&
    -0.07
     الممكن
    -0.07
     จาก
    -0.07
     sembra
    -0.07
     એવું
    -0.07
     pregnant
    -0.07
    POSITIVE LOGITS
     erhältlich
    0.11
     beschikbaar
    0.11
     voljo
    0.10
    accessible
    0.09
     доступны
    0.09
     hieronder
    0.09
    如下
    0.09
     löytyy
    0.09
    organized
    0.09
     verfügbar
    0.09
    Activations Density 0.116%

    No Known Activations