Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43919
    Prev
    Next
    INDEX
    Explanations

    breaking down into parts

    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
    -0.09
    Period
    -0.08
    .Trace
    -0.07
    Mind
    -0.07
     snapshot
    -0.07
     snapshots
    -0.07
    (res
    -0.07
    .Retention
    -0.07
     Extension
    -0.07
    Insertion
    -0.07
    POSITIVE LOGITS
     шин
    0.09
     accompl
    0.08
    aciju
    0.08
     Anmeldung
    0.08
     ચાલી
    0.08
     زمینه
    0.08
     decorated
    0.08
     puh
    0.07
     диплом
    0.07
     besides
    0.07
    Activations Density 0.000%

    No Known Activations