© 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. 99262
    Prev
    Next
    INDEX
    Explanations

    MAC

    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
     lady
    -0.08
     rust
    -0.07
     trolley
    -0.07
     $('#
    -0.07
     obst
    -0.07
     appeal
    -0.07
     eche
    -0.07
    lady
    -0.07
     Appeal
    -0.07
     од
    -0.07
    POSITIVE LOGITS
    叉
    0.09
    Bearer
    0.08
    -bearing
    0.08
     Weapons
    0.07
     subordinate
    0.07
     mediated
    0.07
     Mur
    0.07
     �
    0.07
     घंट
    0.07
     bearer
    0.07
    Activations Density 0.001%

    No Known Activations