© 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. 47307
    Prev
    Next
    INDEX
    Explanations

    locations

    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
     empres
    -0.08
     entreprise
    -0.08
    ే�
    -0.08
    228
    -0.08
     anh
    -0.07
     ifade
    -0.07
    임
    -0.07
     갖
    -0.07
     ite
    -0.07
     réseaux
    -0.07
    POSITIVE LOGITS
    —the
    0.09
     नेतृत्व
    0.08
    里的
    0.08
    _children
    0.08
    _marks
    0.08
    Negoti
    0.08
    ways
    0.08
    上的
    0.08
    /Footer
    0.08
    _die
    0.08
    Activations Density 0.084%

    No Known Activations