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. 52873
    Prev
    Next
    INDEX
    Explanations

    Suggestions and instructions

    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
    _under
    -0.08
    under
    -0.07
    _pending
    -0.07
    _end
    -0.07
    _users
    -0.07
     indefinitely
    -0.07
    äm
    -0.07
    _basic
    -0.07
    _interrupt
    -0.07
    .End
    -0.07
    POSITIVE LOGITS
     actively
    0.10
    actively
    0.10
     динами
    0.09
     പ്രമുഖ
    0.09
     באמת
    0.09
     يوه
    0.09
     konkre
    0.08
     necessarily
    0.08
     tangible
    0.08
     creatively
    0.08
    Activations Density 0.008%

    No Known Activations