© 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. 8072
    Prev
    Next
    INDEX
    Explanations

    The

    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
     drainage
    -0.09
     extrema
    -0.09
     julọ
    -0.09
    -minded
    -0.08
    طح
    -0.08
     эст
    -0.08
     masonry
    -0.08
     »
    -0.08
    ాష్ట్ర
    -0.08
     draining
    -0.08
    POSITIVE LOGITS
     Teacher
    0.09
    npc
    0.09
     Animal
    0.08
     Dentist
    0.08
    Teacher
    0.08
     Coach
    0.08
     Goodbye
    0.07
    Animal
    0.07
    oracle
    0.07
    _density
    0.07
    Activations Density 0.102%

    No Known Activations