© 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. 11-RESID-POST-AA
    11. 78373
    Prev
    Next
    INDEX
    Explanations

    Bacteria

    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
     Erwer
    -0.08
     לב
    -0.08
     IAction
    -0.08
     Hiz
    -0.07
     іст
    -0.07
    _aw
    -0.07
    _GET
    -0.07
    _adv
    -0.07
     الآخر
    -0.07
     Levy
    -0.07
    POSITIVE LOGITS
     environments
    0.10
     ambientes
    0.10
     workplace
    0.08
    环境
    0.08
    вад
    0.08
     bathroom
    0.08
    /tmp
    0.08
     городской
    0.08
     sludge
    0.08
     वातावरण
    0.08
    Activations Density 0.014%

    No Known Activations