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. 74548
    Prev
    Next
    INDEX
    Explanations

    Informative/instructional writing

    np_max-act · gemini-2.0-flash

    marketing-focused guidance on creating effective lead magnets and landing pages.

    oai_token-act-pair · gpt-5-nanoTriggered by @tatsatx
    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
    )।
    -0.09
     parey
    -0.09
    <|reserved_200000|>
    -0.09
     sorkar
    -0.09
    'lgan
    -0.08
     siquiera
    -0.08
    าษา
    -0.08
    বা
    -0.08
     '/')
    -0.08
     "")
    -0.08
    POSITIVE LOGITS
    -
    0.15
    ?
    0.14
    f
    0.14
    ↵
    0.14
    1
    0.14
     T
    0.14
    ↵↵
    0.14
    c
    0.14
     
    0.14
     ↵↵
    0.13
    Activations Density 37.590%

    No Known Activations