© 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. 70170
    Prev
    Next
    INDEX
    Explanations

    firm

    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
     uncont
    -0.10
     Visits
    -0.08
    angent
    -0.08
    �니다
    -0.08
     visit
    -0.08
    county
    -0.08
     nate
    -0.08
     dominar
    -0.07
     visits
    -0.07
     ruler
    -0.07
    POSITIVE LOGITS
     thinkers
    0.08
     गरी
    0.08
    =args
    0.07
     med
    0.07
     parar
    0.07
     trop
    0.07
     Str
    0.07
     strcat
    0.07
    imli
    0.07
     dign
    0.07
    Activations Density 0.001%

    No Known Activations