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. 55880
    Prev
    Next
    INDEX
    Explanations

    part

    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
     Greenland
    -0.08
     Iceland
    -0.08
     cement
    -0.07
     Ett
    -0.07
     Hudson
    -0.07
     Butler
    -0.07
     northeastern
    -0.07
     Hels
    -0.07
     footprint
    -0.07
    纪
    -0.07
    POSITIVE LOGITS
    是多少
    0.10
    ägen
    0.09
    0.08
    Squared
    0.08
     squared
    0.08
     הק
    0.07
    入り
    0.07
     keş
    0.07
    calculator
    0.07
     téléphone
    0.07
    Activations Density 0.009%

    No Known Activations