© 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. 23-RESID-POST-AA
    11. 51799
    Prev
    Next
    INDEX
    Explanations

    cons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чеч
    -0.08
     səh
    -0.08
     torture
    -0.08
    چې
    -0.08
     सुख
    -0.08
    披
    -0.08
     چی
    -0.08
    ్వ
    -0.08
     pamusoro
    -0.08
    Ç
    -0.08
    POSITIVE LOGITS
    ignment
    0.20
    ignee
    0.15
    ignor
    0.14
    igned
    0.14
    ignent
    0.14
    ortium
    0.14
    ign
    0.14
    igner
    0.14
    ignation
    0.14
    ignée
    0.14
    Activations Density 0.002%

    No Known Activations