© 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. 3-RESID-POST-AA
    11. 12789
    Prev
    Next
    INDEX
    Explanations

    梯

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pon
    -0.08
     Pok
    -0.08
     Matthews
    -0.08
     Brass
    -0.08
     geben
    -0.08
     plaques
    -0.08
     Lep
    -0.07
     பிரத
    -0.07
     Luk
    -0.07
     Bike
    -0.07
    POSITIVE LOGITS
     suburban
    0.08
    haven
    0.08
     FOREIGN
    0.07
     racket
    0.07
     submiss
    0.07
     nim
    0.07
     gros
    0.07
    Semester
    0.07
    554
    0.07
    िण
    0.07
    Activations Density 0.001%

    No Known Activations