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. 30015
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities

    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
     fotógrafo
    -0.08
    剑
    -0.08
     verst
    -0.08
     surge
    -0.08
     deut
    -0.08
     ಎಂಬ
    -0.08
     larawan
    -0.08
     syn
    -0.08
     wɔ
    -0.08
     photoc
    -0.07
    POSITIVE LOGITS
    Contribution
    0.08
     Contribution
    0.08
     contribution
    0.08
    -pe
    0.08
    <?>
    0.07
     impli
    0.07
     عرض
    0.07
     admitting
    0.07
     OMX
    0.07
    投入
    0.07
    Activations Density 0.020%

    No Known Activations