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. 103026
    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
     テ
    -0.08
    テ
    -0.08
     TTC
    -0.08
     Michele
    -0.07
     تي
    -0.07
    -aut
    -0.07
     aro
    -0.07
    സ്റ്റ്
    -0.07
    妮
    -0.07
     Mel
    -0.07
    POSITIVE LOGITS
     lists
    0.08
    wps
    0.08
     responsable
    0.08
    _lists
    0.08
    000
    0.08
    Lists
    0.08
    contr
    0.08
    chair
    0.08
     evolucion
    0.07
    커
    0.07
    Activations Density 0.000%

    No Known Activations