© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78326
    Prev
    Next
    INDEX
    Explanations

    Orwell and "1984"

    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
     hesitation
    -0.08
    dbg
    -0.08
    Disp
    -0.07
     तार
    -0.07
     homeowners
    -0.07
    'assurance
    -0.07
     dissolved
    -0.07
     outward
    -0.07
     anglers
    -0.07
     দ্র
    -0.07
    POSITIVE LOGITS
     Orwell
    0.13
     oppressive
    0.11
     dyst
    0.10
     ressent
    0.09
     authoritarian
    0.09
    习近平
    0.08
    生产
    0.08
    inux
    0.08
     oppression
    0.08
     conspiracy
    0.08
    Activations Density 0.003%

    No Known Activations