© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 24746
    Prev
    Next
    INDEX
    Explanations

    in

    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
    �
    -0.09
     sociedad
    -0.08
     sociales
    -0.08
    otras
    -0.08
    軽
    -0.08
     Mec
    -0.08
    ísica
    -0.08
    .number
    -0.07
    کام
    -0.07
     ligera
    -0.07
    POSITIVE LOGITS
    -gallery
    0.08
     шкаф
    0.08
     closets
    0.08
     teak
    0.08
    ictionary
    0.08
    вай
    0.08
     tote
    0.08
     уют
    0.08
     spacious
    0.08
    вайте
    0.08
    Activations Density 0.004%

    No Known Activations