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. 437
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
     חובה
    -0.10
     synonymous
    -0.09
    @return
    -0.08
    }catch
    -0.08
    Sinon
    -0.08
    $MESS
    -0.08
    mandatory
    -0.08
    .Url
    -0.08
    "url
    -0.08
    Committed
    -0.07
    POSITIVE LOGITS
     nestled
    0.09
     sitting
    0.08
    277
    0.08
     Bootstrap
    0.08
     laptop
    0.08
     situated
    0.08
     sits
    0.08
    -centered
    0.08
    Laptop
    0.07
     കാർ
    0.07
    Activations Density 0.007%

    No Known Activations