© 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. 95
    Prev
    Next
    INDEX
    Explanations

    ly

    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
     убрать
    -0.08
     Chen
    -0.08
     Market
    -0.07
     Good
    -0.07
     Pow
    -0.07
     ples
    -0.07
     chien
    -0.07
    amn
    -0.07
    werking
    -0.07
    Chen
    -0.07
    POSITIVE LOGITS
     మంది
    0.11
    Enough
    0.09
     intense
    0.08
    igeze
    0.08
     enough
    0.08
     banget
    0.08
     enemies
    0.08
     kakhulu
    0.07
     genug
    0.07
     случаев
    0.07
    Activations Density 0.022%

    No Known Activations