© 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. 19-RESID-POST-AA
    11. 18819
    Prev
    Next
    INDEX
    Explanations

    Essential

    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
     विभिन्न
    -0.10
     വിവിധ
    -0.09
     Various
    -0.09
     ವಿವಿಧ
    -0.09
     आपके
    -0.09
    各种
    -0.09
     उनके
    -0.09
    .↵
    -0.09
     다양한
    -0.09
     वापस
    -0.09
    POSITIVE LOGITS
     observation
    0.20
    Observation
    0.19
     observations
    0.19
     insight
    0.17
     Observation
    0.17
     idea
    0.16
    Observ
    0.16
     Observ
    0.15
    观察
    0.14
     constraints
    0.14
    Activations Density 0.003%

    No Known Activations