© 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. 23-RESID-POST-AA
    11. 6050
    Prev
    Next
    INDEX
    Explanations

    Game names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icii
    -0.08
    ichita
    -0.08
    �
    -0.08
    ihia
    -0.08
     ouzh
    -0.08
    og
    -0.08
    -imi
    -0.08
    urgia
    -0.07
    ritical
    -0.07
     Ut
    -0.07
    POSITIVE LOGITS
     populaires
    0.09
     populares
    0.09
    LO
    0.08
    لوب
    0.08
    Cats
    0.08
    Snap
    0.08
    lopen
    0.08
    лено
    0.08
    List
    0.08
    לול
    0.08
    Activations Density 0.001%

    No Known Activations