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. 53787
    Prev
    Next
    INDEX
    Explanations

    m

    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
     Christine
    -0.08
     Cue
    -0.07
    ACES
    -0.07
    cendo
    -0.07
    _can
    -0.07
    은
    -0.07
     Mend
    -0.07
     Crisp
    -0.07
     spelling
    -0.07
     Mariano
    -0.07
    POSITIVE LOGITS
     jätt
    0.08
     commodo
    0.08
    jem
    0.08
    。。↵↵
    0.08
     рай
    0.08
    /kg
    0.08
     bayar
    0.08
     arbeit
    0.07
    -temperature
    0.07
     resten
    0.07
    Activations Density 0.006%

    No Known Activations