© 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 EvalsExportsAPI 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. 69403
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
    /home
    -0.08
    .parent
    -0.08
    ,parent
    -0.08
    HOME
    -0.08
     средствами
    -0.08
    ,is
    -0.08
    thi
    -0.08
    _HAS
    -0.07
     сери
    -0.07
    Rt
    -0.07
    POSITIVE LOGITS
     dimensional
    0.09
     faible
    0.09
    -dimensional
    0.09
     Dim
    0.08
     termine
    0.08
     vysok
    0.08
     kleurr
    0.08
     genius
    0.08
    قار
    0.08
     múltiples
    0.07
    Activations Density 0.021%

    No Known Activations