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. 3-RESID-POST-AA
    6. 2354
    Prev
    Next
    INDEX
    Explanations

    Foreshadowing

    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
    _DT
    -0.09
    生命周期
    -0.08
    .templates
    -0.07
    Grade
    -0.07
    FN
    -0.07
    ทธิ
    -0.07
    .cls
    -0.07
    _FN
    -0.07
    eax
    -0.07
     taxed
    -0.07
    POSITIVE LOGITS
    _reserved
    0.09
     summon
    0.09
     imbere
    0.08
     Verl
    0.08
     ав
    0.08
     автоб
    0.08
     Reservations
    0.08
     ase
    0.07
     Seminary
    0.07
     ऐ
    0.07
    Activations Density 0.001%

    No Known Activations