© 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. 26
    Prev
    Next
    INDEX
    Explanations

    lone

    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
     nonsense
    -0.08
     δε
    -0.07
     Früh
    -0.07
    markup
    -0.07
     hygiene
    -0.07
    ായിരുന്നു
    -0.07
    stype
    -0.07
     gegeben
    -0.07
    fund
    -0.07
     മുമ്പ
    -0.07
    POSITIVE LOGITS
     lone
    0.11
    孤
    0.09
     solitary
    0.09
     सैनिक
    0.09
     warrior
    0.09
    stående
    0.08
     pistol
    0.08
    -standing
    0.08
     compañ
    0.08
    �
    0.08
    Activations Density 0.003%

    No Known Activations