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. 77572
    Prev
    Next
    INDEX
    Explanations

    turbine blades

    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
     insomnia
    -0.08
     pragmatic
    -0.08
    itorial
    -0.07
     Prag
    -0.07
     Gazette
    -0.07
    itional
    -0.07
     insult
    -0.07
     inhabited
    -0.07
     conversations
    -0.07
    [temp
    -0.07
    POSITIVE LOGITS
     blades
    0.10
     Renewable
    0.10
     rotor
    0.10
     الشمس
    0.09
     renewable
    0.09
     вращ
    0.09
    叶
    0.09
     lob
    0.09
     серд
    0.08
     Ч
    0.08
    Activations Density 0.005%

    No Known Activations