© 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. 110907
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ambe
    -0.08
     solaire
    -0.08
    -sensitive
    -0.08
    Pregunta
    -0.07
    √
    -0.07
     dié
    -0.07
    messer
    -0.07
    akov
    -0.07
    mig
    -0.07
     masking
    -0.07
    POSITIVE LOGITS
    资金
    0.09
     pressures
    0.09
     venced
    0.08
    0.08
     subsid
    0.08
     legais
    0.08
     owners
    0.08
     foreclosure
    0.08
    意味着
    0.08
     wła
    0.08
    Activations Density 0.021%
    No Known Activations