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

    Neuronpedia

    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. 30405
    Prev
    Next
    INDEX
    Explanations

    mirror image

    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
     Dublin
    -0.08
     Nigerian
    -0.08
     Germ
    -0.08
     Ruh
    -0.08
     redirects
    -0.08
     UDP
    -0.08
     Liverpool
    -0.08
     gardener
    -0.08
     Bombay
    -0.07
     lifespan
    -0.07
    POSITIVE LOGITS
     mirrored
    0.11
    rored
    0.11
    mirror
    0.09
     symmetry
    0.09
    .deepcopy
    0.09
     symmetrical
    0.08
     identical
    0.08
    coord
    0.08
    ingred
    0.08
     svg
    0.08
    Activations Density 0.015%

    No Known Activations