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. 65131
    Prev
    Next
    INDEX
    Explanations

    male

    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
    ця
    -0.08
    ній
    -0.08
     coverings
    -0.08
     happening
    -0.07
    ħabba
    -0.07
    했
    -0.07
    -community
    -0.07
    Ani
    -0.07
     keluarga
    -0.07
    provement
    -0.07
    POSITIVE LOGITS
     Faucet
    0.08
     quitte
    0.08
    LEAR
    0.08
     efetu
    0.08
    -La
    0.08
     леп
    0.07
    �
    0.07
     Gad
    0.07
    .fxml
    0.07
     بە
    0.07
    Activations Density 0.007%

    No Known Activations