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. 45088
    Prev
    Next
    INDEX
    Explanations

    clear

    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
    되는
    -0.08
    .Des
    -0.07
     Jan
    -0.07
    .des
    -0.07
    Exponent
    -0.07
    르는
    -0.07
    Dollar
    -0.07
     chac
    -0.07
    zers
    -0.07
     비롯
    -0.07
    POSITIVE LOGITS
     солне
    0.09
     сав
    0.08
     angen
    0.08
     sunlight
    0.08
     wat
    0.08
     hük
    0.08
     sunny
    0.08
     cloudy
    0.08
     unbel
    0.08
     errs
    0.07
    Activations Density 0.006%

    No Known Activations