© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 68147
    Prev
    Next
    INDEX
    Explanations

    distance between points

    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
     Präs
    -0.08
    Testimonials
    -0.08
     intest
    -0.08
     Ils
    -0.08
     Solomon
    -0.08
     Statistics
    -0.07
    ithe
    -0.07
     nutrition
    -0.07
     Commands
    -0.07
     offences
    -0.07
    POSITIVE LOGITS
     counterpart
    0.09
     counterparts
    0.09
     corresponding
    0.08
     మ్యాచ్
    0.08
     matched
    0.08
    _candidates
    0.08
    Across
    0.08
     movers
    0.08
    对应
    0.08
    require
    0.08
    Activations Density 0.043%

    No Known Activations