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. 8966
    Prev
    Next
    INDEX
    Explanations

    codes, ids, abbreviations

    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
    zend
    -0.09
    ungk
    -0.08
     bango
    -0.08
     Nieuw
    -0.08
    amient
    -0.08
     bermain
    -0.08
     realizada
    -0.08
     Kid
    -0.08
     tenaga
    -0.08
     Maaari
    -0.08
    POSITIVE LOGITS
    iffer
    0.10
    ijkstra
    0.09
    ifferent
    0.08
    oubles
    0.08
    atabase
    0.08
    aughter
    0.08
    aphne
    0.08
    ife
    0.08
    ungeon
    0.08
    Hier
    0.08
    Activations Density 0.036%

    No Known Activations