© 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. 110869
    Prev
    Next
    INDEX
    Explanations

    administrative/selling

    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
    -0.08
     singular
    -0.08
    sing
    -0.08
    ACS
    -0.08
     ফের
    -0.08
    الة
    -0.08
     Welsh
    -0.07
    ati
    -0.07
    安徽
    -0.07
     প্রধান
    -0.07
    POSITIVE LOGITS
    Rum
    0.09
     concepto
    0.08
     candidata
    0.08
     syndrome
    0.08
     río
    0.07
    Viewport
    0.07
     inteira
    0.07
     inventions
    0.07
     remb
    0.07
     ruso
    0.07
    Activations Density 0.003%
    No Known Activations