© 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. 69325
    Prev
    Next
    INDEX
    Explanations

    logical conditions

    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
     Fl
    -0.08
     vah
    -0.08
     anomal
    -0.08
     fluctuations
    -0.07
    ington
    -0.07
     Кат
    -0.07
    \uff
    -0.07
     Puerto
    -0.07
    �s
    -0.07
     fluct
    -0.07
    POSITIVE LOGITS
     jemanden
    0.09
     spies
    0.08
    Fancy
    0.08
     crescer
    0.08
     wachsen
    0.08
     metaph
    0.08
    Growth
    0.07
    (position
    0.07
     speeches
    0.07
    phr
    0.07
    Activations Density 0.008%

    No Known Activations