© 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. 97647
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
    .in
    -0.09
    .bg
    -0.09
     eléctr
    -0.09
    .add
    -0.09
     մանր
    -0.09
    .left
    -0.09
    .ids
    -0.09
     հիմա
    -0.09
    _主页
    -0.09
    ,欧美
    -0.08
    POSITIVE LOGITS
    VALUE
    0.14
    LETTER
    0.13
    STAT
    0.12
    FINITY
    0.12
    LEVEL
    0.12
    MODEL
    0.12
    CLASS
    0.12
    DAY
    0.11
    mazing
    0.11
    TEAM
    0.11
    Activations Density 0.084%

    No Known Activations