© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 24807
    Prev
    Next
    INDEX
    Explanations

    squares

    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
     tom
    -0.08
     tombe
    -0.08
     impetus
    -0.07
     Boc
    -0.07
     Hirsch
    -0.07
     Cher
    -0.07
     جای
    -0.07
     mien
    -0.07
    tom
    -0.07
     showers
    -0.07
    POSITIVE LOGITS
    mates
    0.08
     thirds
    0.08
    Saver
    0.08
    Sul
    0.08
    Craig
    0.08
     Saver
    0.07
     sized
    0.07
     oz
    0.07
    =size
    0.07
    -thirds
    0.07
    Activations Density 0.036%

    No Known Activations