© 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. 70721
    Prev
    Next
    INDEX
    Explanations

    RHS

    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
     footprints
    -0.08
    Fingerprint
    -0.08
     Arctic
    -0.07
     Preservation
    -0.07
    Extr
    -0.07
    Around
    -0.07
    CAC
    -0.07
    extr
    -0.07
     circum
    -0.07
     needless
    -0.07
    POSITIVE LOGITS
    辺
    0.09
     પક્ષ
    0.09
    -side
    0.08
    쪽
    0.08
    most
    0.08
    側
    0.08
    ونا
    0.08
     તરફ
    0.08
     RHS
    0.08
     taraf
    0.08
    Activations Density 0.009%

    No Known Activations