© 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. 19-RESID-POST-AA
    11. 103153
    Prev
    Next
    INDEX
    Explanations

    But

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    -0.10
    base
    -0.09
    equals
    -0.09
    setter
    -0.09
    bv
    -0.09
    skip
    -0.08
    points
    -0.08
    rating
    -0.08
    tos
    -0.08
    method
    -0.08
    POSITIVE LOGITS
     
    0.11
     أصبح
    0.10
    &nbsp
    0.10
     أصبحت
    0.10
     
    0.10
     
    0.10
     
    0.10
     اك
    0.10
     mà
    0.10
    ،
    0.10
    Activations Density 0.028%

    No Known Activations