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. 58949
    Prev
    Next
    INDEX
    Explanations

    r

    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
     Vors
    -0.08
     Authorization
    -0.08
     Checkbox
    -0.08
     Ens
    -0.08
    'ordre
    -0.07
     OPTIONS
    -0.07
     Admin
    -0.07
     Blog
    -0.07
     Caval
    -0.07
    QUENCE
    -0.07
    POSITIVE LOGITS
    Needed
    0.09
    missing
    0.08
    曜日
    0.08
    Partial
    0.08
    �
    0.08
     needing
    0.08
    天
    0.08
    erging
    0.08
    缺
    0.08
     yearning
    0.08
    Activations Density 0.007%

    No Known Activations