© 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. 95381
    Prev
    Next
    INDEX
    Explanations

    Giving information

    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
    solver
    -0.09
    typeparam
    -0.09
     embody
    -0.09
    =forms
    -0.09
     Fórum
    -0.08
    ovno
    -0.08
    reducers
    -0.08
     inspectors
    -0.08
     classical
    -0.08
    	scanf
    -0.08
    POSITIVE LOGITS
     factual
    0.11
     المعلومات
    0.09
     πληροφο
    0.09
     citing
    0.09
     informacje
    0.09
    _info
    0.09
     accurate
    0.09
     Informationen
    0.08
     माहिती
    0.08
    情報
    0.08
    Activations Density 0.129%

    No Known Activations