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. 111952
    Prev
    Next
    INDEX
    Explanations

    support

    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
    Ing
    -0.08
    规模
    -0.08
     Isabella
    -0.07
    �
    -0.07
    ’ing
    -0.07
    812
    -0.07
    582
    -0.07
     overwhelmingly
    -0.07
     intrins
    -0.07
     rumor
    -0.07
    POSITIVE LOGITS
    parm
    0.08
    -strength
    0.08
     protections
    0.08
     parm
    0.08
    desk
    0.08
    突出
    0.08
    力度
    0.07
     crim
    0.07
    ость
    0.07
     Schwer
    0.07
    Activations Density 0.005%

    No Known Activations