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. 11571
    Prev
    Next
    INDEX
    Explanations

    boolean algebra/logic circuits

    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
    .choice
    -0.08
    .impl
    -0.08
    viamente
    -0.08
     metaphor
    -0.07
    Restart
    -0.07
    થી
    -0.07
    Implementation
    -0.07
    _execution
    -0.07
    Delayed
    -0.07
    iex
    -0.07
    POSITIVE LOGITS
     قال
    0.08
    训
    0.08
     kļ
    0.08
     كم
    0.08
     кварт
    0.07
    860
    0.07
     ontstaan
    0.07
     loft
    0.07
     мі
    0.07
     tuner
    0.07
    Activations Density 0.001%

    No Known Activations