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. 113859
    Prev
    Next
    INDEX
    Explanations

    analogies and pattern recognition

    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
     annotate
    -0.09
     multiple
    -0.09
     spekt
    -0.08
     wrap
    -0.07
    _multiple
    -0.07
    multiple
    -0.07
     pointer
    -0.07
    _j
    -0.07
    .wrap
    -0.07
    h
    -0.07
    POSITIVE LOGITS
    规律
    0.09
     impar
    0.08
     Zodiac
    0.08
     ബന്ധ
    0.08
     остальные
    0.08
     ultima
    0.08
     уме
    0.08
     אצל
    0.08
     ряда
    0.08
     cousins
    0.08
    Activations Density 0.025%

    No Known Activations