© 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. 113597
    Prev
    Next
    INDEX
    Explanations

    Software access and configuration

    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
    üg
    -0.10
    -final
    -0.09
    etrize
    -0.08
    lighter
    -0.08
    іда
    -0.08
     longitudinal
    -0.08
     wasi
    -0.08
    _ie
    -0.08
     deriva
    -0.08
    �
    -0.08
    POSITIVE LOGITS
     commun
    0.08
     communes
    0.08
     volver
    0.08
     conspir
    0.08
     Facebook
    0.07
    .facebook
    0.07
    NG
    0.07
     tipping
    0.07
     treffen
    0.07
     unreliable
    0.07
    Activations Density 0.001%

    No Known Activations