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. 43087
    Prev
    Next
    INDEX
    Explanations

    scientific definitions

    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
     presented
    -0.07
     presentada
    -0.07
    旅游
    -0.07
    –
    -0.07
    سل
    -0.07
     apresent
    -0.07
    Lifetime
    -0.07
     wearing
    -0.07
    -present
    -0.07
     presentado
    -0.07
    POSITIVE LOGITS
     Cushion
    0.09
     verhouding
    0.09
     subdiv
    0.09
     Near
    0.09
     thinner
    0.09
     போது
    0.08
     تقس
    0.08
     halfway
    0.08
     finer
    0.08
     Verhältnis
    0.08
    Activations Density 0.005%

    No Known Activations