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. 49041
    Prev
    Next
    INDEX
    Explanations

    clarity

    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
     heavily
    -0.08
    gaming
    -0.07
    Gaming
    -0.07
     hai
    -0.07
     automobil
    -0.07
     Haunted
    -0.07
    modifiable
    -0.07
    Sampler
    -0.07
    ylon
    -0.07
     sam
    -0.07
    POSITIVE LOGITS
     clarity
    0.15
     clare
    0.14
     claridad
    0.14
    晰
    0.13
     clara
    0.11
     Clear
    0.11
     Clare
    0.10
     clearer
    0.10
     claire
    0.10
     পরিষ
    0.10
    Activations Density 0.021%

    No Known Activations