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. 88049
    Prev
    Next
    INDEX
    Explanations

    way

    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
     zuerst
    -0.08
    70
    -0.07
    chi
    -0.07
     Clap
    -0.07
     horrific
    -0.07
    阴
    -0.07
    ì
    -0.07
    χ
    -0.07
     Opfer
    -0.07
    遠
    -0.07
    POSITIVE LOGITS
     belonging
    0.08
     Cyr
    0.08
     teeth
    0.07
     Teeth
    0.07
     traversal
    0.07
     typography
    0.07
    Retries
    0.07
    retain
    0.07
     Inclusion
    0.07
    Traversal
    0.07
    Activations Density 0.005%

    No Known Activations