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. 43755
    Prev
    Next
    INDEX
    Explanations

    Expressing facts/opinions

    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
    .Out
    -0.07
     Out
    -0.07
    anon
    -0.07
    Out
    -0.07
    -0.07
     inspire
    -0.07
     hypothetical
    -0.07
    casino
    -0.07
    /Base
    -0.07
    ivos
    -0.07
    POSITIVE LOGITS
     actually
    0.15
     sebenarnya
    0.14
    actually
    0.14
    实际上
    0.14
     Actually
    0.14
     faktisk
    0.13
    Actually
    0.13
     tatsächlich
    0.13
     faktiskt
    0.12
     वास्तव
    0.12
    Activations Density 0.173%

    No Known Activations