© 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. 129522
    Prev
    Next
    INDEX
    Explanations

    Consumer

    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
     を
    -0.09
    «
    -0.09
     と
    -0.08
     >↵
    -0.08
     ......
    -0.08
    105
    -0.07
     forklift
    -0.07
    Kem
    -0.07
     scall
    -0.07
     �
    -0.07
    POSITIVE LOGITS
    (fd
    0.09
    (dm
    0.09
    (directory
    0.08
    (db
    0.08
    (uri
    0.08
    (texture
    0.08
    (connection
    0.08
    (df
    0.08
    (fs
    0.08
    (area
    0.08
    Activations Density 0.012%

    No Known Activations