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. 105956
    Prev
    Next
    INDEX
    Explanations

    coordinate axes and intercepts

    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
     zusammeng
    -0.08
    frig
    -0.08
     nig
    -0.08
     beruh
    -0.07
    高级
    -0.07
     بیمار
    -0.07
    先进
    -0.07
     Feld
    -0.07
    等级
    -0.07
    -admin
    -0.07
    POSITIVE LOGITS
     CGPoint
    0.09
     CLLocation
    0.08
     nghiệm
    0.08
     Named
    0.08
    tritt
    0.08
     Standort
    0.08
    _named
    0.08
    .Connect
    0.08
    spunkt
    0.08
    .Bounds
    0.08
    Activations Density 0.036%

    No Known Activations