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. 77222
    Prev
    Next
    INDEX
    Explanations

    Power usage effectiveness (PUE)

    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
     densely
    -0.08
     overlapping
    -0.08
    ATAL
    -0.08
    urz
    -0.08
     overlap
    -0.07
     wybor
    -0.07
     abundant
    -0.07
     sites
    -0.07
     overlaps
    -0.07
     adequate
    -0.07
    POSITIVE LOGITS
     모습을
    0.08
    tracked
    0.08
     Smash
    0.08
    idian
    0.07
     Мини
    0.07
    ’S
    0.07
    ipal
    0.07
     Fruit
    0.07
     mourn
    0.07
    _Debug
    0.07
    Activations Density 0.001%

    No Known Activations