© 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. 68040
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     potenti
    -0.08
    ients
    -0.07
    Ens
    -0.07
     نها
    -0.07
    ほど
    -0.07
     صورت
    -0.07
    chestr
    -0.07
     بها
    -0.07
     које
    -0.07
     bagi
    -0.07
    POSITIVE LOGITS
     sedent
    0.09
     hobbies
    0.09
    学历
    0.09
    财经
    0.08
     practising
    0.08
     struggling
    0.08
     educated
    0.08
     WLAN
    0.08
     athletic
    0.08
     unmarried
    0.08
    Activations Density 0.088%

    No Known Activations