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. 43349
    Prev
    Next
    INDEX
    Explanations

    revolutions or resistance

    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
     Unicode
    -0.08
    .Double
    -0.08
     valenc
    -0.08
     idle
    -0.07
     unpack
    -0.07
     thought
    -0.07
    organic
    -0.07
     Slight
    -0.07
    zụ
    -0.07
     uv
    -0.07
    POSITIVE LOGITS
     oppression
    0.18
     oppressive
    0.18
     injustice
    0.14
     injust
    0.13
     crackdown
    0.13
     tyranny
    0.13
     ظلم
    0.12
     authoritarian
    0.12
    侵犯
    0.11
     persecution
    0.11
    Activations Density 0.176%

    No Known Activations