© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 17986
    Prev
    Next
    INDEX
    Explanations

    say "a or perfect"

    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
    Negative Logits
    	New
    -0.09
     Memories
    -0.08
    :name
    -0.08
     ഉപയോഗ
    -0.08
    NETWORK
    -0.08
    UNG
    -0.08
    	with
    -0.08
    dialogs
    -0.08
     advertise
    -0.08
     villains
    -0.08
    POSITIVE LOGITS
     integer
    0.13
     divisible
    0.12
     palindrome
    0.12
    整数
    0.11
     a
    0.11
     any
    0.11
    _integer
    0.10
     exact
    0.10
     positive
    0.10
     arbitrary
    0.09
    Activations Density 0.020%

    No Known Activations