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. 113832
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
    ARD
    -0.08
    &G
    -0.08
    �
    -0.08
     Tig
    -0.07
    Hol
    -0.07
    理解
    -0.07
     calib
    -0.07
    Comp
    -0.07
    :↵↵
    -0.07
     Garr
    -0.07
    POSITIVE LOGITS
     remotely
    0.09
    endale
    0.09
    רים
    0.08
     requisite
    0.08
     Knife
    0.08
     Clover
    0.08
     knife
    0.08
    ớ
    0.08
     sheds
    0.08
    끼
    0.08
    Activations Density 0.226%

    No Known Activations