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. 112091
    Prev
    Next
    INDEX
    Explanations

    wave

    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
     darling
    -0.09
    ition
    -0.08
    controls
    -0.07
    acct
    -0.07
    pix
    -0.07
    gx
    -0.07
     oxid
    -0.07
    ocracy
    -0.07
    goto
    -0.07
     дор
    -0.07
    POSITIVE LOGITS
     waves
    0.10
     Waves
    0.09
    .wave
    0.09
    bands
    0.08
    潮
    0.08
    -wave
    0.08
     Marine
    0.08
     wave
    0.08
    Wave
    0.08
     Tide
    0.08
    Activations Density 0.016%

    No Known Activations