© 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. 11-RESID-POST-AA
    11. 68992
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    learn
    -0.08
     mnemonic
    -0.08
    .learn
    -0.08
     daar
    -0.08
     разобраться
    -0.08
     demonstra
    -0.08
    Mnemonic
    -0.08
     확
    -0.08
    leer
    -0.07
     penny
    -0.07
    POSITIVE LOGITS
     μό
    0.07
     ശേഷം
    0.07
     respecting
    0.07
     fag
    0.07
    之后
    0.07
    ονται
    0.07
     Presence
    0.07
     همچ
    0.07
     Tritur
    0.07
    infection
    0.07
    Activations Density 0.003%

    No Known Activations