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. 103163
    Prev
    Next
    INDEX
    Explanations

    plane

    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
     inzicht
    -0.08
     ਕੰ
    -0.08
     hour
    -0.07
     angle
    -0.07
    Spinner
    -0.07
     ਸੁ
    -0.07
     salas
    -0.07
     tavalla
    -0.07
     spinner
    -0.07
     mois
    -0.07
    POSITIVE LOGITS
    เว
    0.10
    вед
    0.08
    -plane
    0.08
    éb
    0.08
    ড়
    0.08
    plane
    0.08
    বাস
    0.08
     flown
    0.08
    -sectional
    0.08
    েন্স
    0.08
    Activations Density 0.013%

    No Known Activations