© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97475
    Prev
    Next
    INDEX
    Explanations

    Mixed content and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mech
    -0.08
    teva
    -0.07
    נ
    -0.07
     instituted
    -0.07
     hög
    -0.07
    edev
    -0.07
     cycles
    -0.07
     ansch
    -0.07
    tr
    -0.07
     other's
    -0.07
    POSITIVE LOGITS
     Poverty
    0.08
    _requirement
    0.08
    -Alpes
    0.08
     метро
    0.08
     Brilliant
    0.08
    ymce
    0.07
     thinker
    0.07
     purified
    0.07
     Collaborative
    0.07
    Nowadays
    0.07
    Activations Density 0.000%

    No Known Activations