© 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. 103091
    Prev
    Next
    INDEX
    Explanations

    !

    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
    -to
    -0.12
    (s
    -0.11
    ulent
    -0.10
    *r
    -0.10
    -proof
    -0.10
    -based
    -0.10
    `s
    -0.10
    .rb
    -0.10
     echte
    -0.10
    's
    -0.09
    POSITIVE LOGITS
    DOCTYPE
    0.13
    IMPORTANT
    0.13
    important
    0.12
    '↵↵
    0.11
     Important
    0.11
     Dacă
    0.11
     Ако
    0.11
    ↵//↵//
    0.10
     Voici
    0.10
     Here's
    0.10
    Activations Density 0.054%

    No Known Activations