© 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. 19-RESID-POST-AA
    11. 102768
    Prev
    Next
    INDEX
    Explanations

    or

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سید
    -0.08
    verläss
    -0.08
    astikan
    -0.08
     یق
    -0.08
    icularly
    -0.08
     заў
    -0.08
     дұ
    -0.08
     walang
    -0.08
    aimana
    -0.08
    可靠吗
    -0.07
    POSITIVE LOGITS
     partial
    0.52
     partially
    0.51
    Partial
    0.50
     gedeelt
    0.50
    partial
    0.49
    _partial
    0.49
     parcialmente
    0.48
     Partial
    0.48
     parcial
    0.45
    .partial
    0.44
    Activations Density 0.324%

    No Known Activations