© 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. 49774
    Prev
    Next
    INDEX
    Explanations

    say "ment ending"

    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
    à
    -0.08
     schop
    -0.08
    ansch
    -0.08
    Extreme
    -0.08
     txuas
    -0.08
    八
    -0.08
     ankle
    -0.08
    uyla
    -0.08
    あ
    -0.07
    动车
    -0.07
    POSITIVE LOGITS
     forno
    0.08
    illing
    0.08
     wanted
    0.08
     Pap
    0.08
    store
    0.08
    _FOR
    0.08
    rook
    0.08
     breadcrumb
    0.08
    (AP
    0.08
    stores
    0.08
    Activations Density 0.000%

    No Known Activations