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. 55603
    Prev
    Next
    INDEX
    Explanations

    Law of Cosines

    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
     preaching
    -0.10
    .hour
    -0.09
     outreach
    -0.09
     eighteenth
    -0.08
    .filtered
    -0.08
    PLEASE
    -0.08
    公益
    -0.08
     gồm
    -0.08
     withdrew
    -0.08
     genuinely
    -0.08
    POSITIVE LOGITS
     relation
    0.08
     మన
    0.08
    ్స్
    0.07
     tomography
    0.07
     hardness
    0.07
     formula
    0.07
    Equation
    0.07
     startling
    0.07
     horrific
    0.07
    Solve
    0.07
    Activations Density 0.027%

    No Known Activations