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. 111968
    Prev
    Next
    INDEX
    Explanations

    Negation, auxiliary verbs

    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
    ’op
    -0.07
     opér
    -0.07
     bg
    -0.07
    'op
    -0.07
     Moscow
    -0.07
     adv
    -0.07
    _OPERATION
    -0.07
     Operation
    -0.07
     besar
    -0.07
     repart
    -0.07
    POSITIVE LOGITS
    丝
    0.08
     valleys
    0.08
     olsa
    0.08
    絲
    0.08
     וגם
    0.08
    ]");↵
    0.08
     hinweg
    0.08
     melan
    0.08
    盆
    0.08
     غور
    0.07
    Activations Density 0.047%

    No Known Activations