© 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. 78439
    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
    including
    -0.08
    398
    -0.08
    lor
    -0.08
    376
    -0.07
     היו
    -0.07
    Liber
    -0.07
     poj
    -0.07
     Jok
    -0.07
    ಿವೆ
    -0.07
    Pel
    -0.07
    POSITIVE LOGITS
     придум
    0.11
    -нибудь
    0.10
     algún
    0.10
    ડી
    0.09
     alguna
    0.09
     одному
    0.09
     אחד
    0.09
     alguno
    0.09
     preferably
    0.09
    ，比如
    0.09
    Activations Density 0.136%

    No Known Activations