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. 59326
    Prev
    Next
    INDEX
    Explanations

    coding

    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
     Reis
    -0.08
     interfering
    -0.07
     gefällt
    -0.07
     dissertations
    -0.07
     Ronald
    -0.07
     vorg
    -0.07
     joined
    -0.07
     "'
    -0.07
     Morrison
    -0.07
     VAC
    -0.07
    POSITIVE LOGITS
    efe
    0.08
    UK
    0.08
    appa
    0.08
     фин
    0.08
    :utf
    0.08
    adik
    0.08
    eble
    0.08
    arit
    0.08
    Here's
    0.08
    =utf
    0.08
    Activations Density 0.000%

    No Known Activations