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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 56094
    Prev
    Next
    INDEX
    Explanations

    T

    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
     driveway
    -0.08
    �
    -0.08
     cup
    -0.08
     Nails
    -0.08
    gemeinschaft
    -0.07
     Cup
    -0.07
     cirurgia
    -0.07
    -shaped
    -0.07
     manche
    -0.07
     dildo
    -0.07
    POSITIVE LOGITS
     temperatures
    0.15
     Temperaturen
    0.13
    Temperature
    0.13
     temperature
    0.13
     ताप
    0.13
     Temperatur
    0.12
     temperatur
    0.12
     temperaturen
    0.12
    temperature
    0.12
    .temperature
    0.12
    Activations Density 0.008%

    No Known Activations