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. 45059
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     속
    -0.09
    하게
    -0.08
     sembler
    -0.07
     وجه
    -0.07
     ер
    -0.07
     thực
    -0.07
     Oleh
    -0.07
    (IEnumerable
    -0.07
    不仅
    -0.07
    таи
    -0.07
    POSITIVE LOGITS
     OT
    0.07
     fe
    0.07
    lü
    0.07
    irit
    0.07
    Greg
    0.07
    Michael
    0.07
     nutshell
    0.07
     Greg
    0.07
     Crist
    0.07
    gele
    0.07
    Activations Density 0.090%

    No Known Activations