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. 129752
    Prev
    Next
    INDEX
    Explanations

    ty

    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
    וח
    -0.08
     serotonin
    -0.07
     compet
    -0.07
     haben
    -0.07
    card
    -0.07
    brew
    -0.07
    Pb
    -0.07
     Hybrid
    -0.07
    watch
    -0.07
    set
    -0.07
    POSITIVE LOGITS
     centroid
    0.09
     reloc
    0.08
    _FACTOR
    0.08
     monoch
    0.08
    /ref
    0.08
     centru
    0.08
    centration
    0.08
     centred
    0.08
     centr
    0.08
     Cheng
    0.08
    Activations Density 0.002%

    No Known Activations