© 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. 110714
    Prev
    Next
    INDEX
    Explanations

    legal claims/damages

    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
     Andrés
    -0.08
     закры
    -0.08
    .close
    -0.07
    _REMOVE
    -0.07
     zza
    -0.07
    itario
    -0.07
     сос
    -0.07
    ্ম
    -0.07
     shelving
    -0.07
     Kass
    -0.07
    POSITIVE LOGITS
     daños
    0.11
     damages
    0.09
     harm
    0.09
     dommages
    0.09
     daño
    0.09
     Plaintiff
    0.09
     perpetr
    0.09
     harms
    0.09
     inj
    0.08
     víctima
    0.08
    Activations Density 0.007%

    No Known Activations