Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49327
    Prev
    Next
    INDEX
    Explanations

    material

    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
     Ly
    -0.09
    Mom
    -0.08
     Mom
    -0.08
     Dolphins
    -0.08
     Chant
    -0.07
     fabulous
    -0.07
     Pic
    -0.07
     Lara
    -0.07
     Fres
    -0.07
     Rh
    -0.07
    POSITIVE LOGITS
     اولیه
    0.09
     incompetent
    0.08
     �
    0.08
    ా
    0.07
     primas
    0.07
    물
    0.07
    Orden
    0.07
    ్స్
    0.07
     نم
    0.07
     Anglo
    0.07
    Activations Density 0.025%

    No Known Activations