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. 59736
    Prev
    Next
    INDEX
    Explanations

    8

    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
    planation
    -0.08
     laminated
    -0.08
    Luong
    -0.08
    ию
    -0.08
     રજૂ
    -0.08
     persever
    -0.08
     stepped
    -0.07
    resent
    -0.07
     workmanship
    -0.07
     tapered
    -0.07
    POSITIVE LOGITS
    _ipv
    0.08
     arteries
    0.08
    favorite
    0.08
     Wiel
    0.07
     favorito
    0.07
     IPv
    0.07
     पसंद
    0.07
     brothers
    0.07
    �
    0.07
    .favorite
    0.07
    Activations Density 0.000%

    No Known Activations