© 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. 11-RESID-POST-AA
    11. 29587
    Prev
    Next
    INDEX
    Explanations

    already

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .robot
    -0.08
     Gros
    -0.08
    角
    -0.08
     peso
    -0.08
    ത്തു
    -0.08
     يلي
    -0.08
     בא
    -0.08
     eröff
    -0.07
     часы
    -0.07
    _oc
    -0.07
    POSITIVE LOGITS
    already
    0.10
     schon
    0.09
    Already
    0.09
     rồi
    0.09
     already
    0.09
     zaten
    0.08
     pristine
    0.08
     sudah
    0.08
    ready
    0.08
     tayari
    0.08
    Activations Density 0.010%

    No Known Activations