© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 30962
    Prev
    Next
    INDEX
    Explanations

    time passing

    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
    闪
    -0.08
    ocale
    -0.07
    生日
    -0.07
    람
    -0.07
    ibri
    -0.07
    ores
    -0.07
    inux
    -0.07
     кеш
    -0.07
    094
    -0.07
    campo
    -0.07
    POSITIVE LOGITS
     segments
    0.08
     supervising
    0.08
     suunn
    0.08
     executing
    0.08
    _SEG
    0.08
     oversees
    0.07
     behalf
    0.07
     مستق
    0.07
     overseeing
    0.07
     لإن
    0.07
    Activations Density 0.000%

    No Known Activations