© 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. 23-RESID-POST-AA
    11. 49349
    Prev
    Next
    INDEX
    Explanations

    Ed

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atiu
    -0.09
    ator
    -0.08
     tini
    -0.08
     Probate
    -0.08
    aired
    -0.08
     rdr
    -0.08
    áticamente
    -0.08
    ário
    -0.07
    enido
    -0.07
    ARIOS
    -0.07
    POSITIVE LOGITS
    ges
    0.21
    gel
    0.16
    GES
    0.13
    get
    0.13
    gy
    0.12
    gesi
    0.12
    gem
    0.11
    ್ಜ
    0.11
    geme
    0.11
    geb
    0.11
    Activations Density 0.003%

    No Known Activations