© 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. 736
    Prev
    Next
    INDEX
    Explanations

    sort

    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
     aktivit
    -0.10
    am
    -0.08
     ere
    -0.07
    ಸ್ಥ
    -0.07
    arela
    -0.07
     meilleure
    -0.07
    _design
    -0.07
     immobil
    -0.07
     am
    -0.07
    -0.07
    POSITIVE LOGITS
     чуж
    0.08
    击
    0.08
    别人
    0.08
    Adres
    0.08
    擊
    0.08
    छ
    0.08
     aloud
    0.07
    抓
    0.07
     distinto
    0.07
    /sc
    0.07
    Activations Density 0.002%
    No Known Activations