© 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. 64986
    Prev
    Next
    INDEX
    Explanations

    corrosion

    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
     جد
    -0.08
    iving
    -0.08
    एच
    -0.07
     К
    -0.07
     கே
    -0.07
     snprintf
    -0.07
     predict
    -0.07
    gesetzt
    -0.07
     Outdoors
    -0.07
    Perfect
    -0.07
    POSITIVE LOGITS
    钱包
    0.09
    .browser
    0.08
     aam
    0.08
     Browser
    0.08
     crus
    0.08
    背
    0.08
     Cavaliers
    0.07
    wallet
    0.07
     eyeliner
    0.07
     insult
    0.07
    Activations Density 0.000%

    No Known Activations