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. 53274
    Prev
    Next
    INDEX
    Explanations

    -G

    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
     самой
    -0.11
     ძლიერი
    -0.11
     мегӯяд
    -0.11
     რთ
    -0.11
     Nakne
    -0.11
     միշտ
    -0.11
     ҷаҳ
    -0.11
     ցանկացած
    -0.11
     ყოველთვის
    -0.11
     դժվար
    -0.11
    POSITIVE LOGITS
    Test
    0.09
    202
    0.09
    03
    0.09
    01
    0.09
    10
    0.08
    Concept
    0.08
    _test
    0.08
    email
    0.08
    Selection
    0.08
    concept
    0.08
    Activations Density 0.438%

    No Known Activations