Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 98382
    Prev
    Next
    INDEX
    Explanations

    ad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cych
    -0.08
    acf
    -0.08
     Ligne
    -0.07
     gegevens
    -0.07
    .office
    -0.07
    -ger
    -0.07
    Flights
    -0.07
     ligne
    -0.07
     ಪ್ರಕರಣ
    -0.07
    usercontent
    -0.07
    POSITIVE LOGITS
    oration
    0.14
    oring
    0.14
    orer
    0.12
    ored
    0.10
    ores
    0.10
    ore
    0.10
    ulation
    0.10
    rift
    0.10
    �
    0.08
    ORE
    0.08
    Activations Density 0.003%

    No Known Activations