© 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. 19-RESID-POST-AA
    11. 103146
    Prev
    Next
    INDEX
    Explanations

    game

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     investigations
    -0.09
    responses
    -0.08
    ITIES
    -0.08
    irds
    -0.08
     маршру
    -0.08
     responses
    -0.08
     artworks
    -0.08
    odies
    -0.08
     προσπά
    -0.08
     disdain
    -0.08
    POSITIVE LOGITS
     changer
    0.19
    Changer
    0.16
    changer
    0.15
    -changing
    0.15
    breaker
    0.13
     breaker
    0.13
     تغيير
    0.13
    -change
    0.13
    改变
    0.13
     değişt
    0.12
    Activations Density 0.006%

    No Known Activations