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. 55376
    Prev
    Next
    INDEX
    Explanations

    deals

    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
     matric
    -0.08
     physically
    -0.08
     irrigation
    -0.08
     podido
    -0.08
    itrate
    -0.07
     предот
    -0.07
    AFX
    -0.07
     möglicherweise
    -0.07
    -0.07
     progn
    -0.07
    POSITIVE LOGITS
    bomb
    0.08
     tackle
    0.08
    hunt
    0.08
    (bp
    0.07
    jobs
    0.07
    uesday
    0.07
     surplus
    0.07
    Confirm
    0.07
    weekly
    0.07
    vaga
    0.07
    Activations Density 0.005%

    No Known Activations