© 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. 3-RESID-POST-AA
    11. 12877
    Prev
    Next
    INDEX
    Explanations

    erved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hires
    -0.09
     Rip
    -0.08
     लिंक
    -0.08
     repudi
    -0.08
     attracts
    -0.08
    _userdata
    -0.08
     tran
    -0.07
    ional
    -0.07
     Rats
    -0.07
     atraer
    -0.07
    POSITIVE LOGITS
     AJ
    0.09
     عبارة
    0.08
     وجه
    0.08
     aj
    0.07
     സാമ്പ
    0.07
     gek
    0.07
     И
    0.07
     تق
    0.07
     �
    0.07
     внешний
    0.07
    Activations Density 0.004%

    No Known Activations