© 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. 247
    Prev
    Next
    INDEX
    Explanations

    ayan

    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
    ogie
    -0.09
    而言
    -0.09
     أ
    -0.08
    പ്പെടുത്ത
    -0.08
     કરીને
    -0.08
    Pipe
    -0.08
    ขึ้น
    -0.08
    ifico
    -0.08
     �
    -0.08
    ితం
    -0.08
    POSITIVE LOGITS
     것은
    0.09
    다면
    0.09
    다고
    0.08
     priorit
    0.08
    다는
    0.08
     Meta
    0.08
     Kra
    0.07
    estroy
    0.07
     fac
    0.07
     Zoe
    0.07
    Activations Density 0.009%

    No Known Activations