© 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. 15-RESID-POST-AA
    11. 16294
    Prev
    Next
    INDEX
    Explanations

    and

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     消
    -0.09
     entsprechende
    -0.09
    RQ
    -0.08
     বেশ
    -0.08
     এছ
    -0.08
    消
    -0.08
    YTE
    -0.08
     pracht
    -0.07
     merkez
    -0.07
     Rafa
    -0.07
    POSITIVE LOGITS
    Whitespace
    0.10
     spacer
    0.09
     punctuation
    0.09
    Delimiter
    0.09
     spacing
    0.09
    Spacing
    0.09
    Separator
    0.09
    _spacing
    0.09
    하거나
    0.08
    Spacer
    0.08
    Activations Density 0.004%

    No Known Activations