© 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. 91457
    Prev
    Next
    INDEX
    Explanations

    sh

    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
     stø
    -0.08
    DDS
    -0.08
    双方
    -0.08
    <td
    -0.08
     konstr
    -0.08
    /weather
    -0.07
     tred
    -0.07
     frio
    -0.07
    AREA
    -0.07
     proactively
    -0.07
    POSITIVE LOGITS
     neck
    0.09
     abdominal
    0.08
    GING
    0.08
    Classic
    0.08
     dinos
    0.08
     dinosaur
    0.08
     cervical
    0.08
     arch
    0.08
    dominal
    0.08
     pit
    0.08
    Activations Density 0.001%

    No Known Activations