© 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. 19-RESID-POST-AA
    11. 103430
    Prev
    Next
    INDEX
    Explanations

    code equations and symbols

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     profunda
    -0.08
     fria
    -0.08
     способны
    -0.08
    acia
    -0.08
    ati
    -0.07
    .description
    -0.07
    ல்
    -0.07
    ningu
    -0.07
    能
    -0.07
    Таким
    -0.07
    POSITIVE LOGITS
     leto
    0.08
     રમત
    0.08
     wenn
    0.08
     þegar
    0.08
    -Shirt
    0.08
     Unless
    0.08
     pev
    0.08
    _SET
    0.07
    >If
    0.07
     teammate
    0.07
    Activations Density 0.000%

    No Known Activations