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. 112320
    Prev
    Next
    INDEX
    Explanations

    plays

    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
    .mipmap
    -0.09
     raster
    -0.08
     protection
    -0.08
    ကို
    -0.08
     ры
    -0.08
     بسرعة
    -0.08
     이미지
    -0.08
    ,image
    -0.08
    orgon
    -0.08
    ğ
    -0.08
    POSITIVE LOGITS
     poignant
    0.10
     testimon
    0.10
     testimony
    0.09
     diálogo
    0.09
    speaker
    0.09
     dialogue
    0.09
    .dialog
    0.09
    Dialog
    0.09
     dialogues
    0.09
    Dialogue
    0.09
    Activations Density 0.053%

    No Known Activations