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. 76553
    Prev
    Next
    INDEX
    Explanations

    Involuntary/automatic actions

    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
     欧洲
    -0.09
    tevõ
    -0.09
     beef
    -0.08
     وفاق
    -0.08
     التف
    -0.08
     美国
    -0.08
     رسانه
    -0.08
     الولايات
    -0.08
    UDIO
    -0.08
     यूर
    -0.08
    POSITIVE LOGITS
     subconscious
    0.16
     automatic
    0.15
     unconscious
    0.15
    automatic
    0.14
     automatically
    0.13
    Automatic
    0.13
     automatique
    0.13
     automatisch
    0.12
     automatische
    0.12
     Automatic
    0.12
    Activations Density 0.017%

    No Known Activations