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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11809
    Prev
    Next
    INDEX
    Explanations

    medicine

    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
    Accounting
    -0.08
    rook
    -0.08
     bonnet
    -0.08
    -One
    -0.08
    vist
    -0.07
     aver
    -0.07
     prevented
    -0.07
    -Test
    -0.07
    druk
    -0.07
    decoder
    -0.07
    POSITIVE LOGITS
    用途
    0.09
    -making
    0.08
    -oriented
    0.08
     дополн
    0.08
    بت
    0.08
     propósito
    0.08
    .http
    0.08
     બન
    0.08
    ائط
    0.07
     삼
    0.07
    Activations Density 0.011%

    No Known Activations