© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 114135
    Prev
    Next
    INDEX
    Explanations

    Navy

    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
     diminishing
    -0.08
     apres
    -0.07
     könnt
    -0.07
     unir
    -0.07
    (tex
    -0.07
     goth
    -0.07
    JR
    -0.07
     hut
    -0.07
     dune
    -0.07
     ladr
    -0.07
    POSITIVE LOGITS
     Simon
    0.08
     fleets
    0.08
    滨
    0.08
     freak
    0.08
    HQ
    0.08
    raska
    0.08
     Admiral
    0.08
    览
    0.08
     Medina
    0.08
     SEM
    0.08
    Activations Density 0.005%

    No Known Activations