© 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. 49911
    Prev
    Next
    INDEX
    Explanations

    CE

    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
    F
    -0.10
    ulah
    -0.09
    udah
    -0.08
     Federação
    -0.08
    A
    -0.08
    regierung
    -0.08
    ంలో
    -0.08
    ameha
    -0.08
     F
    -0.08
     government
    -0.08
    POSITIVE LOGITS
    fr
    0.09
     marked
    0.09
    marked
    0.09
    Marked
    0.08
    FR
    0.08
    fræð
    0.08
     marking
    0.08
     flask
    0.08
    jax
    0.08
     imọran
    0.08
    Activations Density 0.002%

    No Known Activations