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. 43408
    Prev
    Next
    INDEX
    Explanations

    weak

    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
     Computers
    -0.07
    أل
    -0.07
     Meyer
    -0.07
     pleasing
    -0.07
     gelang
    -0.07
    adino
    -0.07
     �
    -0.07
    بادل
    -0.07
    ख्या
    -0.07
    geen
    -0.07
    POSITIVE LOGITS
    掉
    0.09
     rõ
    0.08
    -hearted
    0.08
    ongan
    0.08
    ATM
    0.08
     osteoporosis
    0.08
     அவ
    0.08
     recess
    0.07
    hood
    0.07
    poke
    0.07
    Activations Density 0.008%

    No Known Activations