© 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. 23-RESID-POST-AA
    11. 47662
    Prev
    Next
    INDEX
    Explanations

    say monetary units/percents

    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
    etermin
    -0.09
    Popover
    -0.08
    reland
    -0.08
    les
    -0.08
    malink
    -0.08
    Bug
    -0.08
    lungs
    -0.08
    leneck
    -0.08
    (cm
    -0.08
    ailure
    -0.08
    POSITIVE LOGITS
     basis
    0.11
     mills
    0.11
     ø
    0.10
     स
    0.10
     Basis
    0.10
     �
    0.09
     ö
    0.09
     hà
    0.09
     आधार
    0.09
     sen
    0.09
    Activations Density 0.008%

    No Known Activations