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. 65085
    Prev
    Next
    INDEX
    Explanations

    (

    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
     investigations
    -0.09
     investigation
    -0.09
    invest
    -0.08
    वाल
    -0.08
     inference
    -0.08
     investigator
    -0.08
    érences
    -0.08
    ş
    -0.07
     propagation
    -0.07
    ifstream
    -0.07
    POSITIVE LOGITS
    Precision
    0.10
     Precision
    0.10
     də
    0.09
    .prec
    0.09
    _precision
    0.09
     precision
    0.09
     DEC
    0.08
     deklar
    0.08
     допуска
    0.08
    Decimals
    0.08
    Activations Density 0.002%

    No Known Activations