© 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. 23-RESID-POST-AA
    11. 5925
    Prev
    Next
    INDEX
    Explanations

    struct

    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
    ur
    -0.09
     නි
    -0.09
    Dub
    -0.08
    -code
    -0.08
     Grupo
    -0.08
     മല
    -0.08
     Trabajo
    -0.08
    -Code
    -0.08
    eco
    -0.08
     hojii
    -0.08
    POSITIVE LOGITS
    angepicker
    0.08
    قاء
    0.08
    ிக்கும்
    0.08
    ়
    0.07
    obot
    0.07
    VS
    0.07
    Joseph
    0.07
    する
    0.07
     así
    0.07
    ுக்கும்
    0.07
    Activations Density 0.000%

    No Known Activations