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. 7-RESID-POST-AA
    6. 1821
    Prev
    Next
    INDEX
    Explanations

    3D models file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inare
    -0.07
    ’esprit
    -0.07
    -estar
    -0.07
     Wang
    -0.07
     Cod
    -0.07
     instituted
    -0.07
    Pot
    -0.07
    utely
    -0.07
     Ear
    -0.07
    Exchange
    -0.07
    POSITIVE LOGITS
     reck
    0.08
     langs
    0.08
     renaissance
    0.08
     tér
    0.08
     arbej
    0.07
    หนัง
    0.07
     Typ
    0.07
     "../../../
    0.07
     мус
    0.07
     داش
    0.07
    Activations Density 0.001%

    No Known Activations