© 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. 111241
    Prev
    Next
    INDEX
    Explanations

    midpoint

    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
    Af
    -0.08
     descriptive
    -0.08
    >,
    -0.07
     badan
    -0.07
    빠
    -0.07
    goed
    -0.07
     ferr
    -0.07
    다
    -0.07
     topical
    -0.07
     കേ
    -0.07
    POSITIVE LOGITS
    -thirds
    0.09
     midpoint
    0.09
     nestled
    0.08
     vị
    0.08
    বর্তী
    0.08
     DISTR
    0.07
    -centered
    0.07
     Calculate
    0.07
    (coords
    0.07
     Korn
    0.07
    Activations Density 0.015%

    No Known Activations