© 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. 23-RESID-POST-AA
    11. 49290
    Prev
    Next
    INDEX
    Explanations

    ident

    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
    ließt
    -0.08
    зал
    -0.08
    XYZ
    -0.08
    ZY
    -0.08
    əz
    -0.08
    з
    -0.08
    ದಲು
    -0.08
     veulent
    -0.08
    зд
    -0.07
     farine
    -0.07
    POSITIVE LOGITS
    ifiant
    0.14
    ificación
    0.11
    ificação
    0.11
    orno
    0.10
    ifi
    0.10
    itaires
    0.10
    ité
    0.10
    ificador
    0.10
    ificacion
    0.10
    ificacao
    0.10
    Activations Density 0.001%

    No Known Activations