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. 30044
    Prev
    Next
    INDEX
    Explanations

    File configuration

    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
     irrespons
    -0.08
     Anatom
    -0.08
     etiquette
    -0.08
     subconscious
    -0.08
     Sampling
    -0.08
     právě
    -0.08
    _RGB
    -0.08
     interns
    -0.08
     RSVP
    -0.08
     Britney
    -0.08
    POSITIVE LOGITS
     daemon
    0.11
     nginx
    0.11
     apache
    0.11
     docker
    0.10
    daemon
    0.10
    apache
    0.10
    Apache
    0.09
     kafka
    0.09
     mysql
    0.09
     wget
    0.09
    Activations Density 0.018%

    No Known Activations