Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49208
    Prev
    Next
    INDEX
    Explanations

    Multilingual text

    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
     whatsoever
    -0.08
    irib
    -0.08
     Zombie
    -0.08
     CALLBACK
    -0.08
     Zudem
    -0.08
     Höhe
    -0.08
    idz
    -0.07
    liefer
    -0.07
     Enn
    -0.07
     CUSTOM
    -0.07
    POSITIVE LOGITS
     നിരവധി
    0.10
     ಹಲವು
    0.10
     ઘણા
    0.09
    很多
    0.09
     कई
    0.09
     عديدة
    0.09
    ,要
    0.09
     പല
    0.09
    来说
    0.09
     easiest
    0.08
    Activations Density 0.082%

    No Known Activations