© 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. 102874
    Prev
    Next
    INDEX
    Explanations

    St

    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
     ে
    -0.09
     uusi
    -0.08
    орая
    -0.08
     presença
    -0.08
    ्ख
    -0.08
    ्कार
    -0.08
    र्ति
    -0.08
    াৱে
    -0.08
     having
    -0.08
    ాంటి
    -0.08
    POSITIVE LOGITS
    .
    0.23
    .~
    0.14
    .-
    0.14
    ۔
    0.13
    .д
    0.13
    .)
    0.13
    ‌.
    0.13
    .'
    0.13
    .Â
    0.13
    .Д
    0.12
    Activations Density 0.014%

    No Known Activations