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. 58353
    Prev
    Next
    INDEX
    Explanations

    domain expansion

    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
     folhas
    -0.08
     fins
    -0.08
    资本
    -0.07
    달
    -0.07
    �
    -0.07
    Alphabet
    -0.07
    දු
    -0.07
     capital
    -0.07
     breaking
    -0.07
     sey
    -0.07
    POSITIVE LOGITS
     분위
    0.10
     surrounds
    0.09
     ambiance
    0.09
     Umgebung
    0.09
     surround
    0.09
     ambience
    0.08
     omgeving
    0.08
     conducive
    0.08
     quarant
    0.08
     containment
    0.08
    Activations Density 0.005%

    No Known Activations