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

    Neuronpedia

    APICircuit 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. 106299
    Prev
    Next
    INDEX
    Explanations

    2

    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
    ield
    -0.09
    IELD
    -0.08
     hardly
    -0.08
     scarcely
    -0.08
     vencer
    -0.07
     சென்னை
    -0.07
     barely
    -0.07
     штат
    -0.07
    afna
    -0.07
    requently
    -0.07
    POSITIVE LOGITS
    Contrast
    0.08
     Contrast
    0.08
     Ond
    0.07
    0.07
     plight
    0.07
     contrast
    0.07
    ਿੰਦ
    0.07
    _ENTRY
    0.07
     GLfloat
    0.07
    .hover
    0.07
    Activations Density 0.000%

    No Known Activations