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. 56200
    Prev
    Next
    INDEX
    Explanations

    pedal

    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
    탈
    -0.09
     welfare
    -0.08
     Bewert
    -0.07
     ṣ
    -0.07
     dictator
    -0.07
     atteindre
    -0.07
    ೊಂದು
    -0.07
    sizeof
    -0.07
     نز
    -0.07
    inet
    -0.07
    POSITIVE LOGITS
     והר
    0.08
     USB
    0.08
    普
    0.08
     postgres
    0.08
    cuits
    0.07
     Peters
    0.07
     Dang
    0.07
    剂
    0.07
     Brace
    0.07
    �
    0.07
    Activations Density 0.001%

    No Known Activations