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. 52918
    Prev
    Next
    INDEX
    Explanations

    _file

    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
    fach
    -0.08
    え
    -0.08
     palpable
    -0.08
     Tapi
    -0.08
    ivals
    -0.07
     ampli
    -0.07
     efectu
    -0.07
    รว
    -0.07
    spa
    -0.07
    buat
    -0.07
    POSITIVE LOGITS
    尺寸
    0.08
    SQL
    0.08
     তাঁ
    0.08
    .SQL
    0.08
    “That
    0.08
     там
    0.07
    ونه
    0.07
     yuav
    0.07
    ovend
    0.07
     מתוך
    0.07
    Activations Density 0.000%

    No Known Activations