© 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 EvalsExportsinterp-engineNEWAPI 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. 70446
    Prev
    Next
    INDEX
    Explanations

    Data analysis and missing data

    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
     overcrow
    -0.08
    �
    -0.07
     évid
    -0.07
    undefined
    -0.07
    comfortable
    -0.07
    -defined
    -0.07
    defined
    -0.07
    ublished
    -0.07
     inherited
    -0.07
    .entry
    -0.07
    POSITIVE LOGITS
    <Person
    0.09
     Persönlichkeit
    0.09
    <Usuario
    0.09
     personality
    0.09
    Pessoa
    0.09
     व्यक्त
    0.09
    _Email
    0.09
    Utilisateur
    0.09
     Personen
    0.09
    Person
    0.08
    Activations Density 0.002%

    No Known Activations