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. 43458
    Prev
    Next
    INDEX
    Explanations

    skin

    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
     menc
    -0.07
     transformational
    -0.07
    )--
    -0.07
    Compat
    -0.07
     Nc
    -0.07
     ខ
    -0.06
     transformative
    -0.06
    lope
    -0.06
     LAP
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     bess
    0.08
    ritt
    0.08
     pouvons
    0.08
     VVD
    0.08
     Ayurveda
    0.07
     тура
    0.07
     vau
    0.07
     Ruiz
    0.07
     roo
    0.07
     Bahrain
    0.07
    Activations Density 0.323%

    No Known Activations