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. 67157
    Prev
    Next
    INDEX
    Explanations

    /

    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
     বিপ
    -0.09
     revolves
    -0.08
     osv
    -0.08
     kinet
    -0.08
     Sicilia
    -0.08
     �
    -0.08
    볼
    -0.08
     bcm
    -0.07
    רים
    -0.07
     뒤
    -0.07
    POSITIVE LOGITS
     Mountain
    0.07
     Länge
    0.07
     mountain
    0.07
     Pixel
    0.07
    _category
    0.07
    serrat
    0.07
     Threat
    0.07
    elong
    0.07
     Fear
    0.07
     Global
    0.07
    Activations Density 0.012%

    No Known Activations