© 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. 62999
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     Inn
    -0.07
     spenn
    -0.07
     Geburtstag
    -0.07
     sobrev
    -0.07
     breit
    -0.07
     জনপ্র
    -0.07
     verschiedene
    -0.07
    stilling
    -0.07
     Größe
    -0.07
     Besonders
    -0.07
    POSITIVE LOGITS
     stakeholders
    0.12
     коллег
    0.11
     colleagues
    0.10
     collaborators
    0.09
     peers
    0.09
    spartner
    0.09
     partenaires
    0.08
     shareholders
    0.08
     artisans
    0.08
    伙伴
    0.08
    Activations Density 0.068%

    No Known Activations