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. 29936
    Prev
    Next
    INDEX
    Explanations

    mettre

    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
    Difficulty
    -0.08
    _H
    -0.08
    Hw
    -0.08
    difficulty
    -0.08
    WE
    -0.08
    icción
    -0.08
     voll
    -0.07
     WE
    -0.07
     ASC
    -0.07
     difficulty
    -0.07
    POSITIVE LOGITS
    活
    0.08
    迹
    0.08
    �
    0.08
    突出
    0.08
    모
    0.07
    促进
    0.07
    -stars
    0.07
     pioneering
    0.07
    ાક
    0.07
     Witch
    0.07
    Activations Density 0.004%

    No Known Activations