© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1043
    Prev
    Next
    INDEX
    Explanations

    igo

    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
     பயன்படுத்த
    -0.08
    -produced
    -0.08
    rekk
    -0.07
    -secret
    -0.07
    /password
    -0.07
     convention
    -0.07
    ימון
    -0.07
     secret
    -0.07
    Secret
    -0.07
     உறுப்ப
    -0.07
    POSITIVE LOGITS
    午後
    0.09
    天空
    0.09
     perg
    0.09
     nahezu
    0.08
     شاهد
    0.08
     почти
    0.08
     ortam
    0.08
     днев
    0.08
    翔
    0.08
    色综合
    0.08
    Activations Density 0.009%

    No Known Activations