© 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. 102687
    Prev
    Next
    INDEX
    Explanations

    .loads

    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
     않았다
    -0.08
    الب
    -0.08
     continents
    -0.07
    년
    -0.07
     hakkında
    -0.07
    مور
    -0.07
    ortun
    -0.07
     imyaka
    -0.07
    -0.07
    ดย
    -0.07
    POSITIVE LOGITS
    ,msg
    0.09
     compliant
    0.08
     તેમજ
    0.08
     Deserialize
    0.08
    STRING
    0.08
    投诉
    0.08
     καθώς
    0.08
     Stimme
    0.08
     denúncia
    0.08
    ulp
    0.08
    Activations Density 0.001%

    No Known Activations