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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 46873
    Prev
    Next
    INDEX
    Explanations

    KHR

    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
     Bucc
    -0.07
    ýn
    -0.07
    entrum
    -0.07
    shire
    -0.07
    _exc
    -0.07
    -->↵↵
    -0.07
    Reserv
    -0.07
     esclus
    -0.07
    小姐
    -0.07
     unfolding
    -0.07
    POSITIVE LOGITS
     professionally
    0.08
     technically
    0.08
     officially
    0.08
    .Destroy
    0.08
    Fact
    0.07
     만드는
    0.07
     fact
    0.07
    бом
    0.07
     certificat
    0.07
     defective
    0.07
    Activations Density 0.003%

    No Known Activations