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. 9174
    Prev
    Next
    INDEX
    Explanations

    floating-point numbers

    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
     Inspect
    -0.08
     Oriente
    -0.08
     insomnia
    -0.08
    온
    -0.08
     Hollow
    -0.08
     검사
    -0.08
    =find
    -0.08
     रोम
    -0.08
     notific
    -0.08
     Onion
    -0.08
    POSITIVE LOGITS
    _percent
    0.10
    _PERCENT
    0.10
    percent
    0.09
    百分
    0.09
     percent
    0.09
    undred
    0.09
    Percent
    0.09
    /Q
    0.08
     numerator
    0.08
     percentage
    0.08
    Activations Density 0.005%

    No Known Activations