© 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. 71235
    Prev
    Next
    INDEX
    Explanations

    前

    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
     cob
    -0.09
    ń
    -0.08
     Maduro
    -0.08
    orption
    -0.08
    gw
    -0.07
     sting
    -0.07
    alchemy
    -0.07
     improper
    -0.07
    icorp
    -0.07
    dol
    -0.07
    POSITIVE LOGITS
    ത്തെ
    0.10
    -facing
    0.10
    面的
    0.10
     సాగ
    0.10
    /front
    0.10
    भाग
    0.10
     allem
    0.09
    -forward
    0.09
    -front
    0.09
     adelante
    0.09
    Activations Density 0.034%

    No Known Activations