© 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. 79065
    Prev
    Next
    INDEX
    Explanations

    relativism and morality

    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
     upscale
    -0.09
    _DS
    -0.08
    מאל
    -0.07
    ;↵↵
    -0.07
     seamless
    -0.07
     nás
    -0.07
    _FULL
    -0.07
     (
    -0.07
    _scale
    -0.07
    -scale
    -0.07
    POSITIVE LOGITS
     perspect
    0.09
    cretion
    0.09
     adulter
    0.08
     whakaaro
    0.08
     refe
    0.08
     lapho
    0.08
     Þegar
    0.08
    gau
    0.08
     նկատմամբ
    0.08
     underm
    0.08
    Activations Density 0.026%

    No Known Activations