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. 78580
    Prev
    Next
    INDEX
    Explanations

    scint

    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
     pron
    -0.08
    270
    -0.08
     excluir
    -0.07
    Excluded
    -0.07
     covenant
    -0.07
    .exclude
    -0.07
    拥有
    -0.07
     yourselves
    -0.07
    Brad
    -0.07
    तान
    -0.06
    POSITIVE LOGITS
     sjón
    0.08
     Nou
    0.08
     annoy
    0.08
    isent
    0.08
     ánh
    0.08
     Tmp
    0.08
     appetite
    0.08
    ციის
    0.08
     hợp
    0.08
     ordentlich
    0.08
    Activations Density 0.001%

    No Known Activations