© 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. 68050
    Prev
    Next
    INDEX
    Explanations

    system interaction instructions

    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
    arest
    -0.08
    abric
    -0.08
    pex
    -0.07
    luss
    -0.07
    umps
    -0.07
    同期
    -0.07
    уса
    -0.07
    Get
    -0.07
     Գր
    -0.07
    _DECLARE
    -0.07
    POSITIVE LOGITS
     midagi
    0.09
     überhaupt
    0.08
     veya
    0.07
     κάτι
    0.07
     glued
    0.07
     должны
    0.07
     شيء
    0.07
     someone's
    0.07
     LE
    0.07
     ή
    0.07
    Activations Density 0.000%

    No Known Activations