Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78707
    Prev
    Next
    INDEX
    Explanations

    10

    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
     bridging
    -0.08
    多数
    -0.08
    掌
    -0.07
     hoffen
    -0.07
     kad
    -0.07
     kamp
    -0.07
     homosexual
    -0.07
     gamma
    -0.07
     irradi
    -0.07
    (Max
    -0.07
    POSITIVE LOGITS
    맛
    0.09
     boutique
    0.09
    -feira
    0.09
     ferrament
    0.08
    бул
    0.08
     plum
    0.08
     SMEs
    0.08
    Ride
    0.08
     серед
    0.08
     boutiques
    0.08
    Activations Density 0.022%

    No Known Activations