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. 77113
    Prev
    Next
    INDEX
    Explanations

    leb

    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
     polarization
    -0.07
    保存
    -0.07
    NW
    -0.07
     Humber
    -0.07
     disponibil
    -0.07
     citing
    -0.07
     Associates
    -0.07
    Sinon
    -0.07
    locations
    -0.07
     Müller
    -0.07
    POSITIVE LOGITS
     capsules
    0.09
    ключ
    0.08
     dancing
    0.08
     ladd
    0.08
     capsule
    0.08
     sadd
    0.08
     beginner
    0.08
    oscopy
    0.08
     गाँ
    0.08
    bells
    0.08
    Activations Density 0.000%

    No Known Activations