© 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. 11-RESID-POST-AA
    11. 71593
    Prev
    Next
    INDEX
    Explanations

    Let

    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
    Negative Logits
    dont
    -0.08
    Placement
    -0.08
     कु
    -0.08
     vestib
    -0.08
    ·
    -0.07
     সচ
    -0.07
    Synchron
    -0.07
     إنتاج
    -0.07
     canal
    -0.07
     تدو
    -0.07
    POSITIVE LOGITS
     Myself
    0.09
    简称
    0.09
    ांकि
    0.08
     denote
    0.08
     temperatura
    0.08
     examine
    0.08
     asum
    0.08
    notations
    0.08
     Parent
    0.07
     hmm
    0.07
    Activations Density 0.036%

    No Known Activations