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. 12730
    Prev
    Next
    INDEX
    Explanations

    90

    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
     എല്ല
    -0.08
    ,
    -0.08
     synonym
    -0.08
     "
    -0.08
     offenbar
    -0.07
    .Sql
    -0.07
     அனை
    -0.07
     apologize
    -0.07
    .
    -0.07
     सबै
    -0.07
    POSITIVE LOGITS
    �
    0.09
    cré
    0.08
     Tup
    0.08
     Hort
    0.08
    hoog
    0.08
     afr
    0.08
     �
    0.08
    picker
    0.08
     Zav
    0.08
    Cré
    0.08
    Activations Density 0.012%

    No Known Activations