© 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 EvalsExportsAPI 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. 64087
    Prev
    Next
    INDEX
    Explanations

    in

    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
     Lief
    -0.08
     theirs
    -0.08
     ours
    -0.08
     hers
    -0.07
    belt
    -0.07
     וש
    -0.07
    ierd
    -0.07
     admite
    -0.07
     yawa
    -0.07
     ibang
    -0.07
    POSITIVE LOGITS
    此同时
    0.12
     котором
    0.10
    spiration
    0.08
     Investigator
    0.08
     inoltre
    0.08
    -inspired
    0.08
     masterpieces
    0.07
     атмос
    0.07
    打造
    0.07
     Immer
    0.07
    Activations Density 0.014%

    No Known Activations