© 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. 71162
    Prev
    Next
    INDEX
    Explanations

    free

    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
    andin
    -0.08
    -I
    -0.08
     GFP
    -0.08
     Schatz
    -0.07
     gern
    -0.07
    .IN
    -0.07
     Animator
    -0.07
    @Rest
    -0.07
    -independent
    -0.07
    versible
    -0.07
    POSITIVE LOGITS
     essentially
    0.08
    латы
    0.08
     prestation
    0.08
     premiums
    0.08
     денег
    0.08
     سنوات
    0.07
     chips
    0.07
    chan
    0.07
    atis
    0.07
    资格
    0.07
    Activations Density 0.018%

    No Known Activations