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. 29908
    Prev
    Next
    INDEX
    Explanations

    physics and equations

    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
     outsourced
    -0.09
     Cayman
    -0.09
     financière
    -0.09
     financial
    -0.09
     Botswana
    -0.08
     Moodle
    -0.08
     accountability
    -0.08
     Bitcoin
    -0.08
     Boxing
    -0.08
     Portugal
    -0.08
    POSITIVE LOGITS
     diffraction
    0.15
     coherence
    0.12
     Fringe
    0.11
     interference
    0.11
     coher
    0.11
     fring
    0.11
     wavelengths
    0.11
     sinc
    0.11
     lasers
    0.11
     fringe
    0.10
    Activations Density 0.006%

    No Known Activations