© 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. 64990
    Prev
    Next
    INDEX
    Explanations

    one-hot encoding

    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
     σημ
    -0.08
    EJB
    -0.08
     ذریعہ
    -0.08
     neuesten
    -0.08
    /song
    -0.07
     द्वारा
    -0.07
     ஆத
    -0.07
    Creature
    -0.07
    CNT
    -0.07
    Slot
    -0.07
    POSITIVE LOGITS
     yani
    0.08
     isu
    0.08
    cludes
    0.07
     accord
    0.07
     એટલે
    0.07
     과정
    0.07
     анг
    0.07
    ("_
    0.07
     Komple
    0.07
     Alan
    0.07
    Activations Density 0.001%

    No Known Activations