© 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. 102452
    Prev
    Next
    INDEX
    Explanations

    Solutions to equations

    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
     averaging
    -0.09
     averaged
    -0.08
     averages
    -0.08
     average
    -0.07
     Renov
    -0.07
     einiger
    -0.07
    -0.07
     promedio
    -0.07
     Aver
    -0.07
     Upgrade
    -0.07
    POSITIVE LOGITS
     είτε
    0.15
    Either
    0.14
    either
    0.14
     entweder
    0.14
     either
    0.13
     Either
    0.12
     oplossingen
    0.12
     zeros
    0.12
    Solutions
    0.12
    Zeros
    0.11
    Activations Density 0.046%
    No Known Activations