Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 48881
    Prev
    Next
    INDEX
    Explanations

    instruction

    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
     péld
    -0.07
     matériel
    -0.07
     buildup
    -0.07
    aly
    -0.07
     Sting
    -0.07
     TPS
    -0.07
     PPS
    -0.07
     accrued
    -0.07
    �
    -0.07
     pj
    -0.07
    POSITIVE LOGITS
     অনুয
    0.09
    事項
    0.09
    사항
    0.08
     사항
    0.08
     zor
    0.08
    事项
    0.08
     مني
    0.08
     মতে
    0.08
    .strict
    0.08
    明确
    0.08
    Activations Density 0.008%

    No Known Activations