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. 54115
    Prev
    Next
    INDEX
    Explanations

    time

    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
    ophyll
    -0.08
    eches
    -0.07
    -aaral
    -0.07
    _pending
    -0.07
    699
    -0.07
     Pending
    -0.07
     Duration
    -0.07
     durations
    -0.07
    vents
    -0.07
    occus
    -0.07
    POSITIVE LOGITS
     veliko
    0.09
    经过
    0.09
    いっぱい
    0.09
     भारी
    0.09
     küll
    0.09
     suut
    0.09
     फै
    0.08
     risultato
    0.08
     asfalt
    0.08
     inmigr
    0.08
    Activations Density 0.032%

    No Known Activations